© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85799
    Prev
    Next
    INDEX
    Explanations

    Honduras, Judge, Ondansetron

    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
     outbound
    0.67
    '
    0.67
     presente
    0.62
    ことなく
    0.59
    csak
    0.58
    in
    0.57
     indors
    0.57
     câteva
    0.57
     aggregator
    0.57
    endant
    0.55
    POSITIVE LOGITS
    ל
    0.83
    з
    0.75
    و
    0.72
    、$
    0.67
    λ
    0.67
    ர
    0.66
    İK
    0.66
    "
    0.64
    ن
    0.64
     you
    0.64
    Activations Density 0.000%

    No Known Activations