© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14866
    Prev
    Next
    INDEX
    Explanations

    bail and hormone reforms

    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_13_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
    bians
    0.57
     whispers
    0.50
     ادي
    0.49
     sounds
    0.47
    。「
    0.46
    ጆ
    0.46
     touchdowns
    0.45
    وون
    0.45
     تكلم
    0.45
    MatContext
    0.44
    POSITIVE LOGITS
    ک
    0.50
    няя
    0.49
    摫
    0.49
     লবণ
    0.47
     رولی
    0.46
     alın
    0.45
     foiled
    0.45
    nina
    0.45
    ey
    0.44
    IER
    0.44
    Activations Density 0.009%

    No Known Activations