© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165200
    Prev
    Next
    INDEX
    Explanations

    UI interactions

    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_13_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
    钲
    0.55
     paisaje
    0.51
     foresee
    0.50
     передба
    0.50
    संगिक
    0.49
     mensen
    0.48
     parku
    0.46
     Netzwerk
    0.46
     condemn
    0.46
     verschiedene
    0.45
    POSITIVE LOGITS
    ']).
    0.50
    ord
    0.50
    ore
    0.50
    ovin
    0.48
    hat
    0.48
    aw
    0.47
    rita
    0.47
    indice
    0.46
    ot
    0.46
    از
    0.46
    Activations Density 0.012%

    No Known Activations