© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76891
    Prev
    Next
    INDEX
    Explanations

    brand name links

    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_31_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
     ouvido
    0.30
     meas
    0.29
     verg
    0.28
     gráfico
    0.27
     Nicola
    0.27
    feito
    0.27
     CHARSET
    0.27
    }"/>
    0.26
    عان
    0.26
    idez
    0.26
    POSITIVE LOGITS
    耺
    0.29
    🔻
    0.29
     tls
    0.28
    zuoye
    0.28
    蒯
    0.28
     कुंड
    0.27
    崦
    0.26
    茧
    0.26
    mirea
    0.26
     Berge
    0.26
    Activations Density 0.001%

    No Known Activations