© 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. 143252
    Prev
    Next
    INDEX
    Explanations

    Prompt

    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
    suffixes
    0.40
    aliya
    0.37
    ália
    0.36
    CHANGE
    0.36
    くい
    0.36
    訳
    0.35
     የስ
    0.35
    ellants
    0.35
     অনুস
    0.35
     చిత్ర
    0.35
    POSITIVE LOGITS
     butterflies
    0.41
    heading
    0.39
    anty
    0.39
     tro
    0.39
     fountain
    0.39
    iseau
    0.38
    椰
    0.38
     aro
    0.38
    ყ
    0.37
     coulomb
    0.37
    Activations Density 0.001%

    No Known Activations