© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207655
    Prev
    Next
    INDEX
    Explanations

    say ";"

    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_56_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
     resc
    0.33
    arca
    0.31
     കൊണ്ട
    0.31
     )(
    0.31
    죵
    0.31
    %)$
    0.31
     ){
    0.30
    𝙘
    0.30
     угла
    0.30
    mfenced
    0.29
    POSITIVE LOGITS
     ऋ
    0.34
    ":
    0.32
    nv
    0.31
    DisplayText
    0.29
    ገ
    0.29
    TypeText
    0.29
    giv
    0.28
    assian
    0.28
    絠
    0.28
     کنند
    0.28
    Activations Density 0.000%

    No Known Activations