© 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. 253307
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     se
    2.55
     се
    2.53
    セ
    2.16
     세
    1.84
     セ
    1.75
     ses
    1.71
     Se
    1.70
    เซ
    1.68
     Се
    1.60
    Се
    1.58
    POSITIVE LOGITS
    regar
    0.44
    runtime
    0.37
    ofield
    0.37
     Einst
    0.36
     చిహ్
    0.35
    riamo
    0.35
    aide
    0.34
    鄞
    0.33
    necks
    0.33
    leftarrow
    0.32
    Activations Density 0.003%

    No Known Activations