© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39835
    Prev
    Next
    INDEX
    Explanations

    h

    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_57_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
    G
    0.48
    Ga
    0.46
    g
    0.46
    SIG
    0.43
    gars
    0.42
    ⴳ
    0.42
    pg
    0.41
    GGG
    0.41
    ag
    0.41
    GI
    0.40
    POSITIVE LOGITS
    <0x97>
    0.86
     H
    0.84
    Ｈ
    0.79
    ｈ
    0.78
     h
    0.77
    ஹ
    0.76
    H
    0.73
    𝗛
    0.72
    𝓗
    0.72
     ah
    0.71
    Activations Density 0.002%

    No Known Activations