© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196336
    Prev
    Next
    INDEX
    Explanations

    faster model

    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_27_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
    痞
    0.40
     cible
    0.40
    Cré
    0.39
     Cycles
    0.39
    cycles
    0.38
    tend
    0.37
    Cycles
    0.37
    ೆಂಟ್
    0.36
     reconocida
    0.36
    湇
    0.36
    POSITIVE LOGITS
     performance
    0.35
     মরদেহ
    0.33
    ныя
    0.33
    bted
    0.32
     further
    0.32
     rumored
    0.32
    我们也
    0.32
     publicly
    0.31
     tiered
    0.31
     outweighed
    0.31
    Activations Density 0.010%

    No Known Activations