© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236245
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    萍
    0.46
    !,
    0.45
    %,
    0.44
     ",
    0.41
     globalisation
    0.41
     tableView
    0.39
    *,
    0.39
    ",
    0.39
    ?,
    0.38
     {},
    0.38
    POSITIVE LOGITS
    ;$
    0.51
    。【
    0.45
    ROTTLE
    0.45
    Ả
    0.44
     auront
    0.44
    ='';
    0.43
     idxf
    0.42
     तथ
    0.42
    ्वेस्ट
    0.42
     tentunya
    0.42
    Activations Density 0.000%

    No Known Activations