© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5327
    Prev
    Next
    INDEX
    Explanations

    manifest.json keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     сфор
    0.26
    Repository
    0.26
    Trash
    0.25
    Filter
    0.25
    Applic
    0.25
    sample
    0.24
    繫
    0.24
    index
    0.23
    filter
    0.23
    Maj
    0.23
    POSITIVE LOGITS
    璧
    0.26
    بول
    0.25
     conversion
    0.24
     শিবির
    0.24
    ध
    0.24
    ्म
    0.24
    鑾
    0.24
     InputAction
    0.24
    राधना
    0.24
     Conversion
    0.24
    Activations Density 0.007%

    No Known Activations