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

    Neuronpedia

    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. 36432
    Prev
    Next
    INDEX
    Explanations

    (Turtles) Ninjas, Turtles

    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
    AR
    0.78
    да
    0.77
    ER
    0.74
    AN
    0.71
    ів
    0.70
    음
    0.66
    ca
    0.66
    غ
    0.66
    ار
    0.64
    য়ে
    0.63
    POSITIVE LOGITS
    0.95
     of
    0.71
     الج
    0.64
    ก
    0.64
     immobil
    0.63
     oe
    0.63
    b
    0.63
    ningar
    0.63
     ekstrem
    0.63
    bels
    0.61
    Activations Density 0.000%

    No Known Activations