© 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. 34593
    Prev
    Next
    INDEX
    Explanations

    list/property/attribute identifiers

    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
     も
    0.74
    ;,
    0.64
     تھی۔
    0.63
    ま
    0.62
    ′,
    0.61
    …).
    0.61
    ,"@
    0.59
    )…
    0.59
    ”…
    0.58
    ,’
    0.57
    POSITIVE LOGITS
    (
    0.86
    :
    0.78
    j
    0.76
    도
    0.70
    io
    0.69
    ın
    0.66
    ől
    0.65
    usions
    0.65
    ía
    0.63
    n
    0.63
    Activations Density 0.018%

    No Known Activations