© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13878
    Prev
    Next
    INDEX
    Explanations

    words related to the structure of formal documents, like instructions, studies, or formal specifications

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

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

    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
    ugd
    -0.49
    «.
    -0.48
    ^(@)
    -0.47
    substack
    -0.46
    CCIÓN
    -0.45
    ?».
    -0.45
    त्रा
    -0.44
    сомо
    -0.44
    """.
    -0.43
    ее
    -0.43
    POSITIVE LOGITS
    ;
    2.70
     ;
    2.06
    ;
    2.03
    ；
    1.99
    .;
    1.80
    ؛
    1.80
    ?;
    1.76
    ;}
    1.74
    ;"
    1.71
    ';
    1.69
    Activations Density 4.560%

    No Known Activations