© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160193
    Prev
    Next
    INDEX
    Explanations

    percentage points

    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_2_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
    ,
    1.40
    in
    1.09
    s
    1.08
    ;
    1.03
    /
    0.98
    The
    0.92
    :
    0.91
    (
    0.88
    0.84
    );
    0.82
    POSITIVE LOGITS
    ί
    0.70
    ွက်
    0.67
    的な
    0.66
    виси
    0.66
    มัน
    0.65
    ಂಕ್
    0.65
    ⇉
    0.65
    豊富な
    0.64
    пециа
    0.64
    াতাড়ি
    0.64
    Activations Density 0.009%

    No Known Activations