© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89297
    Prev
    Next
    INDEX
    Explanations

    control groups, gear, strategies, tower

    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
    ال
    0.80
    lar
    0.78
     is
    0.75
    in
    0.73
    the
    0.73
    w
    0.73
    were
    0.71
    1
    0.70
    ration
    0.69
    bred
    0.69
    POSITIVE LOGITS
     كبير
    0.70
     capace
    0.68
     rodzaj
    0.68
     polizia
    0.68
     veliko
    0.67
     rimane
    0.64
     cura
    0.64
     raggiungere
    0.64
     Є
    0.63
    κι
    0.63
    Activations Density 0.001%

    No Known Activations