© 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. 87145
    Prev
    Next
    INDEX
    Explanations

    "RS" followed by numbers like 232, 485, 256

    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
     d
    0.82
     a
    0.82
    א
    0.81
     i
    0.80
    การ
    0.80
     A
    0.77
    ?
    0.75
     e
    0.71
    Ä
    0.70
     and
    0.70
    POSITIVE LOGITS
    ir
    0.86
    ين
    0.78
    odată
    0.75
    pesar
    0.71
    irió
    0.70
    itoare
    0.70
    ológica
    0.69
    irsi
    0.68
    ur
    0.68
    ónimo
    0.67
    Activations Density 0.002%

    No Known Activations