© 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. 127083
    Prev
    Next
    INDEX
    Explanations

    damn good

    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
    кмекер
    0.67
     altında
    0.67
    ضای
    0.66
    島の
    0.65
     dolayı
    0.63
    (
    0.63
     உள்ளன
    0.63
    nX
    0.61
    ")(
    0.60
    *'
    0.60
    POSITIVE LOGITS
    ే
    0.70
     ungef
    0.66
    he
    0.66
    ول
    0.63
    m
    0.62
    om
    0.61
    de
    0.60
    was
    0.58
    聃
    0.58
    ور
    0.58
    Activations Density 0.000%

    No Known Activations