© 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. 123341
    Prev
    Next
    INDEX
    Explanations

    same old

    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
    u
    0.88
     as
    0.82
    w
    0.68
    트
    0.65
    ہ
    0.62
    ją
    0.60
    hle
    0.59
    이었
    0.59
    지
    0.59
    މ
    0.58
    POSITIVE LOGITS
    '
    1.02
    TEM
    0.85
    2
    0.77
    oc
    0.70
    ка
    0.69
    ’
    0.68
    SIN
    0.65
    RO
    0.65
    ้อ
    0.64
    лом
    0.63
    Activations Density 0.000%

    No Known Activations