© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179199
    Prev
    Next
    INDEX
    Explanations

    params input structure

    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_29_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
     原因
    0.34
    𒁍
    0.33
     entire
    0.31
    agt
    0.30
    Ap
    0.30
    叧
    0.30
    றிய
    0.30
     Relating
    0.30
    只想
    0.30
    ័
    0.30
    POSITIVE LOGITS
     europäischen
    0.36
    ক্র
    0.35
     consistency
    0.35
    consistency
    0.34
    urais
    0.34
     inconsistency
    0.33
    وج
    0.31
     mocked
    0.31
    ოველ
    0.31
     जनक
    0.31
    Activations Density 0.003%

    No Known Activations