© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127307
    Prev
    Next
    INDEX
    Explanations

    haggled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    an
    0.77
    ل
    0.76
    不允许
    0.65
    ৫
    0.64
    是
    0.63
     opdracht
    0.63
    且
    0.62
    л
    0.61
    い
    0.61
    一定要
    0.59
    POSITIVE LOGITS
    ES
    0.82
    IN
    0.78
    IC
    0.77
    ED
    0.76
    EL
    0.76
    RO
    0.74
    ET
    0.73
    RI
    0.72
    IS
    0.71
    IL
    0.70
    Activations Density 0.000%

    No Known Activations