© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48913
    Prev
    Next
    INDEX
    Explanations

    candle.static

    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
     downstairs
    0.38
     rhythmic
    0.38
     clap
    0.36
    단을
    0.36
     rhythm
    0.36
    毋
    0.35
     tap
    0.34
     taps
    0.34
     banged
    0.34
     registers
    0.34
    POSITIVE LOGITS
    quinazoline
    0.38
     атмос
    0.38
     വേദ
    0.37
    大气
    0.37
    ansive
    0.37
    sortTable
    0.37
    缩小
    0.37
    ᖁ
    0.36
    減少
    0.36
    MessageType
    0.36
    Activations Density 0.069%

    No Known Activations