© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20293
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     -,
    1.09
     –,
    1.03
     —,
    1.02
     *,
    0.95
     /,
    0.95
     '.',
    0.94
     &,
    0.93
    /,
    0.92
     ।,
    0.91
     (),
    0.90
    POSITIVE LOGITS
     вре
    0.36
    ими
    0.35
    楎
    0.35
     interp
    0.34
    िमम
    0.33
    alaman
    0.33
     кем
    0.33
     Martinez
    0.33
    활동
    0.32
    慥
    0.32
    Activations Density 0.269%

    No Known Activations