© 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. 124382
    Prev
    Next
    INDEX
    Explanations

    Names and specific terms

    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
    t
    0.87
    ר
    0.72
    a
    0.71
    tive
    0.71
    tio
    0.69
     posit
    0.67
     querido
    0.67
    n
    0.66
     afili
    0.64
     and
    0.62
    POSITIVE LOGITS
    in
    0.94
    ны
    0.80
    at
    0.75
    atlar
    0.74
    to
    0.64
    ных
    0.63
    as
    0.62
    վել
    0.61
    ong
    0.59
     ಸ್ಥಳ
    0.57
    Activations Density 0.000%

    No Known Activations