© 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. 15713
    Prev
    Next
    INDEX
    Explanations

    a mishmash of words relating to personal narrative.

    oai_token-act-pair · 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
    Географиясе
    -0.70
    ьаж
    -0.65
    ніципа
    -0.60
    自己是
    -0.59
     resourceCulture
    -0.57
     vực
    -0.56
     فريبيس
    -0.56
    bleshooting
    -0.55
     venons
    -0.54
     propria
    -0.54
    POSITIVE LOGITS
    ους
    0.54
    )++;
    0.52
    $")
    0.50
     />';
    0.48
    ัตว์
    0.47
    chieben
    0.47
     ***/
    0.47
    τουργ
    0.46
    MENAFN
    0.45
    tizers
    0.45
    Activations Density 15.124%

    No Known Activations