© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 164544
    Prev
    Next
    INDEX
    Explanations

    you could say I'm doing

    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
    ocal
    0.34
    önet
    0.33
    aldo
    0.33
    very
    0.32
    formal
    0.32
    Very
    0.32
     गायक
    0.32
    *_
    0.32
     very
    0.31
    beach
    0.31
    POSITIVE LOGITS
     whoever
    0.39
     hela
    0.34
    整
    0.34
     मागणी
    0.34
     Whoever
    0.34
    ௭
    0.34
     hini
    0.33
    绪
    0.33
     arou
    0.33
     Babel
    0.33
    Activations Density 0.003%

    No Known Activations