© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194850
    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_15_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
     CHE
    0.50
     L
    0.50
     W
    0.49
     palette
    0.48
    ну
    0.47
     U
    0.46
     conventional
    0.45
     fibrous
    0.45
    ці
    0.45
     physically
    0.44
    POSITIVE LOGITS
    Funds
    0.52
    Pods
    0.51
    Fault
    0.50
    familyName
    0.49
    uhe
    0.47
     audiencia
    0.47
    㭂
    0.47
    お金
    0.47
    TypeCode
    0.46
    nCount
    0.46
    Activations Density 0.000%

    No Known Activations