© 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. 14577
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and political terms

    oai_token-act-pair · gemini-2.0-flash

    numerical data and financial terms

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

    Monetary amounts and statistics

    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
     ErrIntOverflow
    -0.57
     fumée
    -0.57
     noDo
    -0.56
    Gambas
    -0.53
    lgari
    -0.53
    onomía
    -0.52
     suç
    -0.52
     prisonniers
    -0.51
     cuivre
    -0.51
     malheur
    -0.50
    POSITIVE LOGITS
    出版年
    0.59
    IsMutable
    0.52
     Cro
    0.50
     nakalista
    0.47
    cr
    0.47
    rfloor
    0.47
    AndEndTag
    0.46
    Sense
    0.46
    sense
    0.46
     cr
    0.46
    Activations Density 3.637%

    No Known Activations