© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205780
    Prev
    Next
    INDEX
    Explanations

    under the control of

    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_6_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
    ин
    1.14
     μια
    1.06
    ای
    0.95
    که
    0.95
    точ
    0.93
    持つ
    0.93
    ರ
    0.93
    се
    0.90
    ст
    0.89
    所の
    0.89
    POSITIVE LOGITS
     be
    0.95
    ları
    0.93
    د
    0.89
     are
    0.89
    ák
    0.89
     on
    0.87
     c
    0.85
     o
    0.85
     ó
    0.82
    h
    0.81
    Activations Density 0.000%

    No Known Activations