© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 7587
    Prev
    Next
    INDEX
    Explanations

    width attribute, virus names, wonders of the world

    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
    на
    3.23
    z
    2.97
    о
    2.70
    ഹ്ലാ
    2.61
     тем
    2.55
     Ă
    2.43
     coveted
    2.42
    rj
    2.38
    ഹ്ലാദ
    2.37
    ^{-
    2.34
    POSITIVE LOGITS
    გილ
    2.97
    maras
    2.59
     misalkan
    2.56
     बैठे
    2.45
    儡
    2.36
    hipp
    2.31
    robe
    2.29
    Tried
    2.23
    ිනි
    2.23
     fecha
    2.20
    Activations Density 0.000%

    No Known Activations