© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13218
    Prev
    Next
    INDEX
    Explanations

    words, amounts, or units of measure followed by the preposition "of"

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     itſelf
    -0.93
    <bos>
    -0.93
    SharedDtor
    -0.90
     >=",
    -0.83
    Geplaatst
    -0.82
     समीक्षक
    -0.77
    ंदीखरीदारी
    -0.74
     myſelf
    -0.71
     Мексичка
    -0.71
     himſelf
    -0.71
    POSITIVE LOGITS
    enken
    0.48
    latform
    0.48
    כשיו
    0.44
    例文帳に追加
    0.44
    ubu
    0.43
    (',');
    0.41
    Ich
    0.41
    דת
    0.41
    kirchen
    0.41
     proprietà
    0.41
    Activations Density 17.165%

    No Known Activations