© 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. 123325
    Prev
    Next
    INDEX
    Explanations

    restless

    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
    x
    0.77
    vacc
    0.67
    clé
    0.67
    lt
    0.65
     и
    0.64
    spaced
    0.64
    an
    0.63
    ł
    0.61
    െ
    0.60
     Deutschlands
    0.60
    POSITIVE LOGITS
    '
    1.05
    د
    0.95
    ’
    0.81
     resid
    0.80
    ↵↵
    0.72
    %
    0.71
     Residency
    0.70
    ム
    0.70
     residency
    0.69
    áme
    0.69
    Activations Density 0.000%

    No Known Activations