© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209982
    Prev
    Next
    INDEX
    Explanations

    into

    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_10_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
    кови
    0.38
    வந்த
    0.34
    кович
    0.34
    ково
    0.33
    didReceive
    0.32
    ун
    0.32
    ።
    0.32
    ₚ
    0.31
    nione
    0.31
    .");
    0.31
    POSITIVE LOGITS
    at
    0.46
     into
    0.42
    ना
    0.37
    ↵
    0.35
    >
    0.32
    ف
    0.31
     Into
    0.31
    <
    0.30
    o
    0.30
     INTO
    0.29
    Activations Density 0.029%

    No Known Activations