© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77999
    Prev
    Next
    INDEX
    Explanations

    formatting instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     Fancy
    0.43
     aband
    0.39
    ♚
    0.39
     ткани
    0.38
     BufferedWriter
    0.38
     fancy
    0.38
    拒绝
    0.38
    )}}{\
    0.37
     Umm
    0.37
     Sự
    0.37
    POSITIVE LOGITS
     চট্টগ্রামের
    0.40
     bes
    0.38
     fortemente
    0.37
    GroupID
    0.36
     iron
    0.36
    גם
    0.35
    代表人
    0.35
     realistically
    0.35
     Grover
    0.34
    +)
    0.34
    Activations Density 0.000%

    No Known Activations