© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33528
    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_7_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
    y
    0.58
     Of
    0.53
    yse
    0.53
     Literature
    0.52
    s
    0.50
     of
    0.50
     limitation
    0.47
     Breaking
    0.47
     Geometry
    0.47
    的选择
    0.47
    POSITIVE LOGITS
    у
    0.67
    о
    0.66
     ヴィ
    0.60
    вин
    0.57
    ви
    0.56
    ujemo
    0.55
    ଁ
    0.53
     parad
    0.53
    도
    0.53
    на
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.