© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203263
    Prev
    Next
    INDEX
    Explanations

    where to find

    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
    );
    1.03
     powied
    0.97
    ).
    0.94
    )*
    0.87
    ა
    0.86
    тся
    0.85
     불구하고
    0.83
    ');
    0.82
    ';
    0.82
     уви
    0.82
    POSITIVE LOGITS
    n
    1.64
    ir
    1.41
    id
    1.41
    p
    1.39
    y
    1.39
    i
    1.34
    un
    1.31
    m
    1.30
    it
    1.29
    l
    1.29
    Activations Density 0.006%

    No Known Activations