© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218916
    Prev
    Next
    INDEX
    Explanations

    your link affiliate

    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_31_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
     core
    0.33
     serviços
    0.32
    ]]->
    0.30
     services
    0.30
     Vite
    0.30
     localVarAccept
    0.30
     inward
    0.30
    lja
    0.30
    vij
    0.29
    faces
    0.29
    POSITIVE LOGITS
    クロマト
    0.34
     डिस्क्रिप्शन
    0.33
     اولم
    0.33
    Polynomial
    0.33
     Chromat
    0.32
    रियो
    0.32
     مم
    0.32
     ጡ
    0.31
     patiently
    0.31
    ibli
    0.30
    Activations Density 0.001%

    No Known Activations