© 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. 3774
    Prev
    Next
    INDEX
    Explanations

    words that reflect a change of state or progress

    oai_token-act-pair · gemini-2.0-flash

    the word "randomly" and punctuation usage

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

    say "ly" words

    np_max-act-logits · gemini-2.0-flash
    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
    PreferredItem
    -0.90
    styleType
    -0.84
    ValueStyle
    -0.80
    AsUp
    -0.75
     disambiguazione
    -0.73
    )];
    -0.73
    expandindo
    -0.73
    "},
    -0.71
     ModelExpression
    -0.71
    TagMode
    -0.70
    POSITIVE LOGITS
    .
    0.56
     genoux
    0.49
    ObjectModel
    0.48
     szól
    0.46
     hoping
    0.44
     faccia
    0.44
     enfrentan
    0.44
     ouvriers
    0.42
     juger
    0.42
     sesso
    0.42
    Activations Density 10.132%

    No Known Activations