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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4870
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

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

    verbs and nouns that indicate taking action or planning of an event

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    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
    ConstraintMaker
    -1.28
    RenderAtEndOf
    -1.18
     فريبيس
    -1.16
     GenerationType
    -1.13
     betweenstory
    -1.13
    #+#
    -1.12
    expandindo
    -1.11
    ReusableCell
    -1.09
     ―――――
    -1.09
    webElementXpaths
    -1.07
    POSITIVE LOGITS
    .
    0.96
    ,
    0.75
    !
    0.67
     and
    0.58
    ;
    0.54
     –
    0.51
    :
    0.50
    ?
    0.49
     —
    0.48
     -
    0.48
    Activations Density 18.332%

    No Known Activations