© 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. 124023
    Prev
    Next
    INDEX
    Explanations

    Donne

    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
    h
    0.68
     yattha
    0.59
     creamy
    0.58
    v
    0.55
    c
    0.54
    0.54
     animale
    0.52
     erinnert
    0.52
     spettacolo
    0.52
     أرض
    0.52
    POSITIVE LOGITS
    ❽
    0.80
    tf
    0.74
     Yards
    0.72
    Да
    0.70
    Balances
    0.70
    necessary
    0.68
     معنی
    0.68
    {
    0.67
    valid
    0.66
    db
    0.66
    Activations Density 0.000%

    No Known Activations