© 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. 14464
    Prev
    Next
    INDEX
    Explanations

    the word "at" even when it is part of a phrase

    oai_token-act-pair · gemini-2.0-flash

    contextually significant words with high latitude

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

    at

    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
     unknownFields
    -0.84
    principalTable
    -0.73
     Waray
    -0.67
    //
    -0.66
     initComponents
    -0.66
    <?
    -0.63
    InvalidProtocol
    -0.61
    Демографія
    -0.60
    matchCondition
    -0.59
    getColumnIndex
    -0.59
    POSITIVE LOGITS
    adaptiveStyles
    0.47
    タジー
    0.46
     souple
    0.45
     fermés
    0.45
     forskning
    0.44
     spese
    0.44
    #+#
    0.44
    SIZES
    0.44
    twimg
    0.44
    tschafts
    0.44
    Activations Density 0.671%

    No Known Activations