© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9704
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    їз
    0.83
     Carta
    0.82
     gegenüber
    0.80
     studied
    0.77
     Zeus
    0.77
    ড়ের
    0.77
    Ⴚ
    0.77
    ᾗ
    0.76
    ánd
    0.74
     Cascade
    0.73
    POSITIVE LOGITS
    user
    1.00
     user
    0.94
    用户
    0.82
    User
    0.80
    users
    0.79
     users
    0.75
     usuario
    0.71
     usuário
    0.70
     User
    0.69
    ユーザー
    0.69
    Activations Density 0.008%

    No Known Activations