© 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. 122323
    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
    ы
    0.65
     éste
    0.65
     stricter
    0.65
     announcing
    0.64
    ยา
    0.63
    ן
    0.60
     epinephrine
    0.60
     anunció
    0.59
     scolded
    0.59
     vaguely
    0.59
    POSITIVE LOGITS
    t
    0.95
    i
    0.82
    g
    0.76
    and
    0.74
    ik
    0.74
    ت
    0.74
    。
    0.74
    وم
    0.73
    et
    0.72
    ij
    0.72
    Activations Density 0.000%

    No Known Activations