© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221358
    Prev
    Next
    INDEX
    Explanations

    Take damage

    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_31_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
     addition
    0.43
     Ру
    0.41
     ரூ
    0.40
    疫苗
    0.40
    addition
    0.38
     onze
    0.38
     vår
    0.38
    ҹ
    0.38
    μον
    0.37
     bombas
    0.37
    POSITIVE LOGITS
     जीता
    0.42
    PNG
    0.38
    దా
    0.37
     हीरा
    0.37
    Gift
    0.37
     फें
    0.35
     Bele
    0.35
    ிழ
    0.35
    Violet
    0.35
    펭
    0.35
    Activations Density 0.002%

    No Known Activations