© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91309
    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_3_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
    '
    1.04
    나
    0.84
    ین
    0.79
    你
    0.78
    라
    0.72
    ی
    0.71
    یہ
    0.71
     you
    0.70
    یط
    0.69
    itamins
    0.68
    POSITIVE LOGITS
    ER
    0.80
    0.69
    ;
    0.69
    AL
    0.67
    P
    0.65
    S
    0.65
    SC
    0.64
    EE
    0.64
    O
    0.64
    šnji
    0.62
    Activations Density 0.000%

    No Known Activations