© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193345
    Prev
    Next
    INDEX
    Explanations

    format specifiers

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    咡
    0.46
    金属
    0.39
    追
    0.37
    zięk
    0.37
     "\""
    0.36
    ША
    0.36
    йде
    0.36
    yní
    0.35
    Copper
    0.35
    臤
    0.35
    POSITIVE LOGITS
     topology
    0.39
     reels
    0.38
     stance
    0.36
    apsing
    0.35
     combustibles
    0.35
    iguous
    0.34
    clerosis
    0.34
     counsels
    0.34
     Mbps
    0.34
    opath
    0.33
    Activations Density 0.010%

    No Known Activations