© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171215
    Prev
    Next
    INDEX
    Explanations

    acidic/sour

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ac
    2.33
     Ac
    2.22
    Ac
    2.06
    ac
    1.77
     AC
    1.38
    AC
    1.21
     acorn
    1.18
    <0x92>
    1.11
     एसी
    1.02
     Acme
    1.01
    POSITIVE LOGITS
     ки
    1.09
     кисло
    1.05
    산
    0.95
    酸
    0.93
     acidic
    0.88
    산을
    0.88
     acid
    0.87
     산
    0.86
     Acid
    0.83
    Acid
    0.80
    Activations Density 0.002%

    No Known Activations