© 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. 206244
    Prev
    Next
    INDEX
    Explanations

    Catalina Island

    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
    Justin
    0.73
    า
    0.73
     Londra
    0.69
    由
    0.68
    く
    0.64
    Samuel
    0.64
    </h3>
    0.64
     forze
    0.64
    א
    0.64
     cei
    0.63
    POSITIVE LOGITS
    inian
    0.71
    als
    0.68
    ainment
    0.68
    ments
    0.67
    ene
    0.65
    en
    0.65
    ata
    0.65
    elt
    0.64
    entino
    0.64
    lera
    0.64
    Activations Density 0.000%

    No Known Activations