© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154857
    Prev
    Next
    INDEX
    Explanations

    end

    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_50_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
    𝗿
    0.41
     осуществля
    0.41
     FPR
    0.40
    மன்
    0.39
    خ
    0.38
    бах
    0.38
     acry
    0.37
    avnom
    0.36
     Adler
    0.36
     selectively
    0.35
    POSITIVE LOGITS
     end
    0.93
     End
    0.85
    端
    0.78
     END
    0.73
    End
    0.71
    エンド
    0.69
     Endo
    0.67
     端
    0.66
    端的
    0.66
     نهاية
    0.64
    Activations Density 0.026%

    No Known Activations