© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42084
    Prev
    Next
    INDEX
    Explanations

    hypertrophy or hyperopt

    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_3_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
    I
    0.68
    r
    0.61
    nala
    0.57
    OrCallback
    0.55
    aniline
    0.54
    grim
    0.54
    nove
    0.54
    mergeddata
    0.54
    opters
    0.54
    ncol
    0.54
    POSITIVE LOGITS
    0.98
    。
    0.72
    ות
    0.72
     to
    0.68
     as
    0.68
     of
    0.67
    、
    0.67
    ↵↵
    0.66
     from
    0.66
    ৮
    0.65
    Activations Density 0.001%

    No Known Activations