© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196940
    Prev
    Next
    INDEX
    Explanations

    Devanagari, Rule, Caro-Kann, Dynasty, Benoist

    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_4_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
     was
    0.19
     to
    0.16
    }
    0.15
     as
    0.15
    ;
    0.14
     be
    0.14
     but
    0.14
     is
    0.14
     and
    0.14
    D
    0.13
    POSITIVE LOGITS
    м
    0.14
    ம்
    0.13
     comenc
    0.13
     provoqu
    0.13
     navegador
    0.12
     campione
    0.12
     consegu
    0.12
     uporab
    0.12
     prawd
    0.12
    ം
    0.12
    Activations Density 0.001%

    No Known Activations