© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197161
    Prev
    Next
    INDEX
    Explanations

    ports and mappings

    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_26_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
     pak
    0.45
    邺
    0.42
     honti
    0.39
     complic
    0.38
    pak
    0.37
     삼
    0.36
     tigers
    0.36
     confer
    0.36
     whirl
    0.36
     invasions
    0.35
    POSITIVE LOGITS
    [],
    0.44
    autoprefixer
    0.42
    chai
    0.40
    handles
    0.40
    duck
    0.39
    мино
    0.39
    CHP
    0.38
     destined
    0.38
     නිසා
    0.38
    幡
    0.38
    Activations Density 0.001%

    No Known Activations