© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61821
    Prev
    Next
    INDEX
    Explanations

    listing items or descriptions

    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
     t
    0.70
    最
    0.57
    ip
    0.53
     merged
    0.51
     ponctu
    0.50
     thân
    0.50
     plupart
    0.50
    usto
    0.50
     a
    0.49
     mén
    0.49
    POSITIVE LOGITS
    am
    0.70
    IZE
    0.61
    LIE
    0.61
    al
    0.59
    Race
    0.59
    Debit
    0.58
    RAR
    0.58
    Glasses
    0.58
    Avro
    0.58
    Ability
    0.57
    Activations Density 0.033%

    No Known Activations