© 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. 44470
    Prev
    Next
    INDEX
    Explanations

    answer choice or key

    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
    ur
    0.88
    ુ
    0.78
    le
    0.76
    it
    0.75
     Präsident
    0.72
    يت
    0.70
    ز
    0.67
    is
    0.66
    ре
    0.66
    يق
    0.66
    POSITIVE LOGITS
    1
    0.78
     kosakata
    0.66
     elementów
    0.66
     ospiti
    0.65
     (
    0.64
    don
    0.64
     nuo
    0.63
     armada
    0.63
     setTimeout
    0.63
    ±
    0.63
    Activations Density 0.010%

    No Known Activations