© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56309
    Prev
    Next
    INDEX
    Explanations

    bloating and irritability

    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_11_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
    ール
    0.55
     exchange
    0.54
    OTP
    0.53
    exchange
    0.52
    ８
    0.52
     scambio
    0.51
    卍
    0.51
    花
    0.50
     ROUTES
    0.50
    交換
    0.49
    POSITIVE LOGITS
     derzeit
    0.49
     röm
    0.46
     myriad
    0.45
     hauptsächlich
    0.44
     sichtbar
    0.44
     trotz
    0.44
     lain
    0.44
     گزشتہ
    0.44
    ish
    0.43
    جل
    0.43
    Activations Density 0.036%

    No Known Activations