© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102546
    Prev
    Next
    INDEX
    Explanations

    breaking down into sections or categories

    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_16_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
    橿
    0.35
    the
    0.34
    s
    0.32
    WART
    0.31
    harm
    0.31
    chester
    0.31
    Microsoft
    0.30
    nutrition
    0.30
    enjoy
    0.30
    y
    0.30
    POSITIVE LOGITS
     saves
    0.31
     eyelids
    0.31
     étapes
    0.30
     Clutch
    0.30
     क्लोरीन
    0.30
     eyes
    0.30
     కే
    0.30
     skis
    0.30
     வாச
    0.29
     ци
    0.29
    Activations Density 0.041%

    No Known Activations