© 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. 121582
    Prev
    Next
    INDEX
    Explanations

    from the

    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
     einzigen
    0.39
    ᾳ
    0.39
     kurzen
    0.38
    ῷ
    0.38
    ർഷ
    0.38
     versões
    0.37
    VERSION
    0.36
    pipes
    0.36
    ACO
    0.36
    孅
    0.36
    POSITIVE LOGITS
     standpoint
    0.53
     тар
    0.45
     afar
    0.44
     onwards
    0.42
     whence
    0.42
     vantage
    0.41
     supplémentaires
    0.39
     ጋር
    0.38
    ？
    0.38
    ーーーー
    0.38
    Activations Density 0.001%

    No Known Activations