© 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. 12781
    Prev
    Next
    INDEX
    Explanations

    scoring, offense, and double-doubles

    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
     maak
    0.38
    ⾃
    0.36
    ீஸ்
    0.36
    Resp
    0.36
     ಮೀ
    0.36
     만들
    0.35
    testimonial
    0.35
     demarcation
    0.35
     vec
    0.35
    琵
    0.35
    POSITIVE LOGITS
     double
    0.66
     Double
    0.61
    double
    0.59
     डबल
    0.57
    Double
    0.57
     doubles
    0.49
    ダブル
    0.48
     doble
    0.47
     doppia
    0.47
     Doubles
    0.46
    Activations Density 0.010%

    No Known Activations