© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243294
    Prev
    Next
    INDEX
    Explanations

    code punctuation/symbols

    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_40_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
    وما
    0.38
    ଧ
    0.38
     chilling
    0.37
     Programm
    0.36
     छल
    0.36
    ára
    0.36
     publie
    0.35
    Faster
    0.35
    ган
    0.35
     Technological
    0.34
    POSITIVE LOGITS
    тол
    0.40
     کردی
    0.38
     suffis
    0.37
    dimg
    0.36
    screw
    0.35
     screws
    0.35
    胯
    0.35
     KP
    0.35
    ipedia
    0.34
    鐺
    0.34
    Activations Density 0.014%

    No Known Activations