© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40996
    Prev
    Next
    INDEX
    Explanations

    what extent does

    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_11_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
    ил
    0.77
    ᅨ
    0.68
    smoothed
    0.60
    𝒌
    0.59
    продук
    0.59
    torque
    0.59
    𝚓
    0.59
    fence
    0.58
     рука
    0.58
    ほん
    0.58
    POSITIVE LOGITS
     Skills
    0.64
     Time
    0.64
    der
    0.63
    0.63
     g
    0.58
    );
    0.58
     Slavery
    0.55
     Magic
    0.55
     writes
    0.54
     learned
    0.54
    Activations Density 0.010%

    No Known Activations