© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141113
    Prev
    Next
    INDEX
    Explanations

    color adjustments and curves

    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_12_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
    rend
    0.64
    .&
    0.58
    .
    0.56
    _
    0.56
    &
    0.56
    hend
    0.55
     &
    0.55
    <0x9B>
    0.54
    or
    0.54
    (&
    0.53
    POSITIVE LOGITS
     پیغم
    0.63
     DEPENDENCIA
    0.62
     quais
    0.61
     proporcional
    0.59
     لیګ
    0.57
    䀎
    0.57
     предполагает
    0.56
     تغ
    0.55
    㧔
    0.55
     catap
    0.54
    Activations Density 0.000%

    No Known Activations