© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27316
    Prev
    Next
    INDEX
    Explanations

    touchdowns, end zones, football

    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_40_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
     flagged
    0.49
     flag
    0.46
    Flag
    0.45
    旗
    0.45
     flags
    0.45
     Flag
    0.44
    FLAG
    0.44
     pelt
    0.43
     Flags
    0.42
     FLAG
    0.41
    POSITIVE LOGITS
     end
    0.98
     End
    0.88
     END
    0.81
    End
    0.80
    end
    0.77
    エンド
    0.71
    端
    0.71
     Endo
    0.69
    END
    0.68
     Endgame
    0.68
    Activations Density 0.002%

    No Known Activations