© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 208639
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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_20_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
     빠르게
    0.19
     lingue
    0.18
     riche
    0.18
     mère
    0.18
     ł
    0.17
     gerecht
    0.17
    ਧੀ
    0.17
     ricotta
    0.17
    혔
    0.17
     掛け
    0.17
    POSITIVE LOGITS
    our
    0.18
    rm
    0.17
    Composite
    0.16
    calls
    0.16
    ore
    0.16
    the
    0.16
    ov
    0.15
    C
    0.15
    void
    0.15
    number
    0.15
    Activations Density 0.003%

    No Known Activations