© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220973
    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_10_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
     terrified
    0.56
     fouled
    0.56
    މ
    0.52
     drained
    0.52
     ruthless
    0.51
    データ
    0.50
    νε
    0.50
    Під
    0.49
    硣
    0.49
     électriques
    0.49
    POSITIVE LOGITS
    B
    0.55
     I
    0.49
    fora
    0.46
    at
    0.46
    apurna
    0.45
    ie
    0.45
    for
    0.45
     SARS
    0.45
    shine
    0.44
    and
    0.44
    Activations Density 0.000%

    No Known Activations