© 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. 33949
    Prev
    Next
    INDEX
    Explanations

    oblate spheroid

    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
     propel
    0.95
    ك
    0.92
    ۳
    0.78
     Fabrizio
    0.76
     boreal
    0.76
    i
    0.76
    ي
    0.74
     predisposition
    0.73
     sprinter
    0.71
     Corolle
    0.71
    POSITIVE LOGITS
     on
    0.98
    ation
    0.73
    ens
    0.68
    ong
    0.66
    lt
    0.66
    ↵
    0.65
    ations
    0.64
    ain
    0.64
    mp
    0.64
    life
    0.63
    Activations Density 0.004%

    No Known Activations