© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211034
    Prev
    Next
    INDEX
    Explanations

    shove

    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_5_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
    diversity
    1.09
     cái
    1.00
    ell
    0.95
    alia
    0.94
    vär
    0.91
    𝗮
    0.91
    kval
    0.91
    on
    0.89
    computing
    0.88
    ucco
    0.87
    POSITIVE LOGITS
    ли
    1.87
    주
    1.46
    >
    1.44
    ;
    1.38
    *
    1.37
     (
    1.36
    \
    1.33
    `
    1.27
    ];
    1.26
    (
    1.25
    Activations Density 0.000%

    No Known Activations