© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104256
    Prev
    Next
    INDEX
    Explanations

    sit/sat on

    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_1_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
    ER
    1.06
    MEN
    1.00
    3
    0.96
    торой
    0.95
    اا
    0.95
    U
    0.93
    UZ
    0.93
    K
    0.93
     Въ
    0.92
     Behandlung
    0.90
    POSITIVE LOGITS
    ین
    1.27
    কে
    1.22
    ’
    1.12
     as
    1.09
     or
    1.07
     erreurs
    1.05
     industry
    1.05
     arrêt
    1.01
    ת
    1.00
     isotopes
    0.99
    Activations Density 0.001%

    No Known Activations