© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142989
    Prev
    Next
    INDEX
    Explanations

    shortly:

    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_0_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
    1.77
     at
    1.43
     for
    1.25
    ?
    1.22
     I
    1.20
    .
    1.16
     C
    1.02
    !
    1.02
     Epistle
    0.99
     U
    0.98
    POSITIVE LOGITS
    ق
    2.05
    та
    1.96
    ع
    1.82
    ка
    1.78
    ك
    1.77
    મ
    1.68
    ק
    1.66
    も
    1.62
    ש
    1.57
    де
    1.56
    Activations Density 0.000%

    No Known Activations