© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141901
    Prev
    Next
    INDEX
    Explanations

    slang, L, W, cap, bars, mama

    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_12_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
    ar
    0.36
    ”，
    0.34
    ans
    0.32
    afft
    0.31
    fak
    0.31
    f
    0.31
    gau
    0.31
    4
    0.31
    left
    0.30
    谎
    0.30
    POSITIVE LOGITS
     Mentre
    0.36
     Alice
    0.34
     TAR
    0.33
     BE
    0.33
     QS
    0.33
     Neil
    0.32
     BIS
    0.32
     Netflix
    0.31
     Lewis
    0.31
     RA
    0.31
    Activations Density 0.000%

    No Known Activations