© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42234
    Prev
    Next
    INDEX
    Explanations

    operating system commands

    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_22_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
    啤酒
    0.33
     drzew
    0.33
     nowego
    0.33
    径
    0.32
    温度
    0.31
     техні
    0.31
    diameter
    0.31
    晿
    0.31
    rabbit
    0.31
    宥
    0.30
    POSITIVE LOGITS
     Available
    0.42
    Available
    0.37
    ubmit
    0.36
     available
    0.35
    Muse
    0.35
     Disponible
    0.34
     হউক
    0.34
     Midlands
    0.34
    Mel
    0.34
    ensington
    0.34
    Activations Density 0.096%

    No Known Activations