© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176131
    Prev
    Next
    INDEX
    Explanations

    names and markers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Mati
    0.42
     Sensing
    0.42
    <0x9C>
    0.40
    擰
    0.40
    ್ರೆ
    0.39
    ಬೇಕ
    0.39
    写真
    0.38
    िकुलर
    0.37
    naden
    0.37
    ље
    0.36
    POSITIVE LOGITS
     제출
    0.38
    vline
    0.37
    जै
    0.37
    헹
    0.36
    ziej
    0.36
     هنت
    0.36
     VH
    0.36
    共有
    0.36
     hairstyles
    0.35
     개최
    0.35
    Activations Density 0.000%

    No Known Activations