© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134118
    Prev
    Next
    INDEX
    Explanations

    Desktop App or Environment

    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_6_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
    ల
    0.93
     alluvial
    0.82
    ून
    0.80
    ↵↵
    0.79
     heur
    0.79
     sicht
    0.79
    드
    0.78
     svært
    0.78
    ਾ
    0.77
     예를
    0.75
    POSITIVE LOGITS
     in
    1.43
    ,
    1.38
    i
    1.35
    to
    1.34
    as
    1.20
    o
    1.17
    r
    1.14
    can
    1.13
    by
    1.12
    and
    1.10
    Activations Density 0.003%

    No Known Activations