© 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. 8157
    Prev
    Next
    INDEX
    Explanations

    James

    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
    ्य
    3.29
    Cheese
    2.83
    Ꭲ
    2.81
    𝐍
    2.79
    त
    2.65
     ढंग
    2.56
    𝘦
    2.55
    дается
    2.50
    Ꭰ
    2.50
    ுகிறது
    2.50
    POSITIVE LOGITS
     провер
    2.90
    ない
    2.66
     itertools
    2.61
    ないと
    2.59
    tip
    2.56
    મો
    2.48
    er
    2.48
    agré
    2.47
    ^{-}
    2.45
    ^{-}$
    2.44
    Activations Density 0.000%

    No Known Activations