© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89579
    Prev
    Next
    INDEX
    Explanations

    chris hay, marshall, woakes, lane, nolan, masterson, christie

    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_3_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
     Și
    0.89
    يد
    0.64
    ’
    0.64
    هاي
    0.64
    UF
    0.63
     },
    0.62
    il
    0.61
     Abschnitt
    0.61
     };
    0.60
    يا
    0.60
    POSITIVE LOGITS
    舗
    0.61
    ять
    0.59
    they
    0.58
    ną
    0.57
     uttering
    0.57
    ively
    0.57
    .
    0.57
     expenses
    0.56
    ması
    0.56
    ्सा
    0.56
    Activations Density 0.000%

    No Known Activations