© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89965
    Prev
    Next
    INDEX
    Explanations

    Anal, Soda, toe, van, English

    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
    k
    0.71
     geografia
    0.68
     proteine
    0.65
    keme
    0.63
    ת
    0.63
     beheld
    0.62
     awoke
    0.61
    ো
    0.61
     kiểm
    0.59
     vět
    0.59
    POSITIVE LOGITS
    of
    0.84
    text
    0.75
    are
    0.69
    ای
    0.68
    label
    0.67
    all
    0.66
    arki
    0.66
    boiler
    0.65
    frac
    0.64
    rest
    0.64
    Activations Density 0.001%

    No Known Activations