© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236477
    Prev
    Next
    INDEX
    Explanations

    C++ function signatures

    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_32_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
     Growing
    0.38
    umm
    0.37
    UM
    0.37
    type
    0.37
     Electroly
    0.36
     Eventually
    0.36
    ]").
    0.36
    作文
    0.35
    Chars
    0.35
     কাউন্স
    0.35
    POSITIVE LOGITS
     মতে
    0.37
    *\
    0.37
     विध
    0.37
     getBitmap
    0.37
     gameOver
    0.37
    জিস্ট
    0.37
     udd
    0.35
     nutmeg
    0.35
     యొక్క
    0.34
     ಆ
    0.34
    Activations Density 0.001%

    No Known Activations