© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38864
    Prev
    Next
    INDEX
    Explanations

    new work or task

    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
    ↵
    0.77
     доби
    0.63
     adept
    0.58
          
    0.57
    <unused2172>
    0.57
     distill
    0.57
    }(
    0.56
    ⁸
    0.55
    ([
    0.55
     pequeños
    0.55
    POSITIVE LOGITS
    ي
    0.82
    ET
    0.79
    י
    0.78
    as
    0.69
    ak
    0.67
    IN
    0.66
     Connecticut
    0.66
    ेंसिल
    0.64
    я
    0.64
    אנ
    0.63
    Activations Density 0.003%

    No Known Activations