© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7975
    Prev
    Next
    INDEX
    Explanations

    specific instruction prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ೃಷ್ಣ
    2.57
     scrutiny
    2.53
    于
    2.45
     Peu
    2.44
     iar
    2.43
    膊
    2.42
    ITIES
    2.39
     đẩy
    2.37
     ngunit
    2.35
     dàng
    2.34
    POSITIVE LOGITS
    ية
    2.60
     seas
    2.18
    as
    2.14
     monet
    2.12
    $(".
    2.11
     quanta
    2.11
    ного
    2.10
     zee
    2.07
    जिये
    2.02
    च
    2.01
    Activations Density 0.000%

    No Known Activations