© 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. 232328
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    (
    1.44
    িক
    1.12
    ী
    1.11
    t
    1.07
    이었
    1.04
    -
    1.04
    و
    0.99
    NE
    0.95
    لي
    0.94
    ில்
    0.92
    POSITIVE LOGITS
     is
    1.08
     malicious
    1.02
     मौलिक
    0.99
     daqu
    0.98
     cinquième
    0.93
     nuova
    0.93
     serotonin
    0.92
     पाँच
    0.92
     cervical
    0.91
     programmatic
    0.91
    Activations Density 0.000%

    No Known Activations