© 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-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235714
    Prev
    Next
    INDEX
    Explanations

    constructor

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     (†
    0.44
     ((*
    0.42
     particulates
    0.40
     ä
    0.39
     $("
    0.39
    レーター
    0.38
    ButtonClicked
    0.38
    äd
    0.38
     Viewed
    0.37
     }(\
    0.37
    POSITIVE LOGITS
    Grat
    0.41
    G
    0.40
     നിന്നും
    0.40
    是个
    0.39
    From
    0.39
     extensible
    0.39
    <?
    0.38
     Mosca
    0.38
    strict
    0.38
     Grat
    0.37
    Activations Density 0.001%

    No Known Activations