© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    4. 32885
    Prev
    Next
    INDEX
    Explanations

    in detail

    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_7_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
    с
    0.36
    us
    0.35
    ag
    0.35
     was
    0.35
     would
    0.35
    ز
    0.35
    ene
    0.34
    og
    0.34
    к
    0.33
    the
    0.33
    POSITIVE LOGITS
     acorns
    0.34
     inclinations
    0.32
     indiquer
    0.30
     angels
    0.29
    Giá
    0.29
     asympt
    0.29
     souvenirs
    0.29
     outbursts
    0.29
     eyeliner
    0.28
     Airy
    0.28
    Activations Density 0.002%

    No Known Activations