© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130781
    Prev
    Next
    INDEX
    Explanations

    color gray variants

    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_1_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
    1.88
    ل
    1.35
    to
    1.32
    in
    1.17
     be
    1.14
     (
    1.12
    z
    1.06
    as
    1.04
    써
    0.99
    the
    0.98
    POSITIVE LOGITS
    ED
    1.18
    AG
    1.05
    ING
    1.05
    AGN
    0.98
    EX
    0.97
    EV
    0.97
    EE
    0.93
    OX
    0.92
    EF
    0.91
    AST
    0.90
    Activations Density 0.000%

    No Known Activations