© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133774
    Prev
    Next
    INDEX
    Explanations

    tumblr posts

    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_37_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
    <0xDE>
    0.44
    ilingual
    0.42
    Blocked
    0.40
    面包
    0.40
    iawan
    0.39
    邀请
    0.39
    qua
    0.39
     displayName
    0.39
     flank
    0.38
    hhhh
    0.37
    POSITIVE LOGITS
    fol
    0.38
     antic
    0.38
    voir
    0.37
    ).-
    0.37
     Abt
    0.36
     DCC
    0.35
    bour
    0.35
    ;-
    0.35
     Seg
    0.34
     inci
    0.34
    Activations Density 0.000%

    No Known Activations