© 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. 7339
    Prev
    Next
    INDEX
    Explanations

    times of

    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
    ی
    1.95
    𝙤
    1.89
    ባድ
    1.82
     Hälfte
    1.79
    зации
    1.76
    𝙄
    1.74
     terceros
    1.71
    ्टी
    1.71
     Bereichen
    1.66
    ين
    1.65
    POSITIVE LOGITS
    ح
    1.81
    ே
    1.74
    є
    1.73
     reputation
    1.70
    LED
    1.65
    गेटिव
    1.65
    al
    1.65
    স
    1.65
     اسلامی
    1.65
    а
    1.63
    Activations Density 0.039%

    No Known Activations