© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36027
    Prev
    Next
    INDEX
    Explanations

    books by Sincere, Froud, Sivers

    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
    وطه
    0.43
    
    0.41
    \-
    0.40
     
    0.39
    \}-
    0.39
    】-
    0.38
    ونة
    0.38
    arsipkan
    0.38
    —-
    0.37
    }--
    0.36
    POSITIVE LOGITS
    .{
    0.43
    .,
    0.39
    ችል
    0.39
    .`
    0.37
     Capital
    0.35
     Shah
    0.35
     Xu
    0.35
    шкин
    0.35
    .,"
    0.35
    .\\
    0.34
    Activations Density 0.001%

    No Known Activations