© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29803
    Prev
    Next
    INDEX
    Explanations

    stint or frenzy

    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_10_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
    크
    0.94
    ྥ
    0.82
    三
    0.80
    ગ
    0.79
    일
    0.76
    蛏
    0.74
    ﭼ
    0.73
    КО
    0.72
    <0xAB>
    0.72
    ၷ
    0.72
    POSITIVE LOGITS
    ↵↵
    0.88
    า
    0.82
     který
    0.79
    z
    0.78
    j
    0.78
    era
    0.76
    asen
    0.73
     والذي
    0.71
                   
    0.70
    ász
    0.69
    Activations Density 0.001%

    No Known Activations