© 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. 36565
    Prev
    Next
    INDEX
    Explanations

    Greene, duck, chicken, hose, doctor

    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
    ING
    0.83
    AR
    0.82
    AN
    0.74
    OM
    0.69
    O
    0.66
    IN
    0.66
    IS
    0.66
    il
    0.64
    F
    0.64
    ent
    0.63
    POSITIVE LOGITS
    عي
    0.67
    ux
    0.62
    ires
    0.61
    冪
    0.58
    "
    0.57
    in
    0.56
    왜
    0.55
     dificult
    0.55
    晶
    0.54
    ните
    0.54
    Activations Density 0.001%

    No Known Activations