© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14391
    Prev
    Next
    INDEX
    Explanations

    allows to indicate

    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_13_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
     हॉ
    0.60
     thách
    0.57
     bốn
    0.55
     nghệ
    0.53
    \%),
    0.52
     Morphology
    0.52
     serie
    0.51
    ϫ
    0.51
     Hör
    0.50
     desafíos
    0.50
    POSITIVE LOGITS
    }
    0.59
    Aqua
    0.56
     equipment
    0.55
    ing
    0.54
    AY
    0.53
     analyzer
    0.53
     chy
    0.52
     regulator
    0.52
     ligament
    0.52
     بواسط
    0.52
    Activations Density 0.015%

    No Known Activations