© 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. 34374
    Prev
    Next
    INDEX
    Explanations

    variable names in code initializers

    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
     reorgan
    0.36
     expedit
    0.36
     Owl
    0.34
     exped
    0.34
    ayı
    0.33
     Alternate
    0.33
    Owl
    0.33
    ⬥
    0.33
    }]_{
    0.33
     alternate
    0.32
    POSITIVE LOGITS
     verso
    0.38
    لوں
    0.36
    ಿಕೊಂಡ
    0.36
     προς
    0.36
    墳
    0.36
     fridge
    0.36
    یف
    0.36
    उने
    0.36
    蹈
    0.36
    ждый
    0.35
    Activations Density 0.004%

    No Known Activations