© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90196
    Prev
    Next
    INDEX
    Explanations

    roles, instructions, tasks

    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_11_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
    by
    0.50
    of
    0.49
     [
    0.48
     by
    0.47
    dat
    0.45
     evanescent
    0.45
    nya
    0.44
     renewed
    0.44
     hated
    0.43
    normalized
    0.43
    POSITIVE LOGITS
    ции
    0.54
    Roles
    0.51
    Tarefa
    0.50
    Impact
    0.50
    Heritage
    0.50
    人材
    0.50
    轍
    0.49
    bí
    0.48
    铎
    0.48
    Equations
    0.47
    Activations Density 0.000%

    No Known Activations