© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46474
    Prev
    Next
    INDEX
    Explanations

    beach

    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
    arse
    0.84
    تح
    0.73
     importantes
    0.73
     tratado
    0.69
    ambda
    0.68
     conjuntos
    0.68
     impressively
    0.68
    <0x80>
    0.68
     numerosos
    0.68
     elevados
    0.68
    POSITIVE LOGITS
     \
    0.91
    ”
    0.89
    ul
    0.81
    다
    0.81
    ا
    0.79
    code
    0.74
    ENT
    0.73
    4
    0.73
    li
    0.73
    o
    0.72
    Activations Density 0.000%

    No Known Activations