© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3446
    Prev
    Next
    INDEX
    Explanations

    words indicating the text is about the opinions, actions, experiences, or recommendations of authors.

    oai_token-act-pair · gemini-2.0-flash

    punctuation and segment markers

    np_token-act-pair-logits · gpt-4o-mini

    punctuation and conditionals

    np_max-act-logits · gemini-2.0-flash

    say "punctuation or sentence-start"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.85
    "],
    -0.84
    NewUrlParser
    -0.83
    ConstraintMaker
    -0.82
    )];
    -0.82
    🏻‍♀️
    -0.81
    "])
    -0.81
    "):
    -0.81
     utafitiHapana
    -0.81
    "]
    -0.80
    POSITIVE LOGITS
    .
    0.71
    ,
    0.57
     while
    0.57
    !
    0.56
    ;
    0.52
     when
    0.50
    ContentAlignment
    0.43
     if
    0.41
    :
    0.40
    ?
    0.40
    Activations Density 34.696%

    No Known Activations