© 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. 7443
    Prev
    Next
    INDEX
    Explanations

    ' End Sub' Delete' HeaderAssuming

    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
    ियत
    2.52
     задума
    2.35
     prestige
    2.30
     wechseln
    2.19
    ᆨ
    2.15
    ური
    2.12
     eryth
    2.12
     esophagus
    2.10
     депозиттик
    2.08
    egrave
    2.05
    POSITIVE LOGITS
    ش
    2.65
    y
    2.52
    नहीं
    2.23
    er
    2.17
    其他
    2.11
    न
    2.10
    m
    2.07
    spaper
    2.06
    coded
    1.98
    ب
    1.95
    Activations Density 0.002%

    No Known Activations