© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59043
    Prev
    Next
    INDEX
    Explanations

    qualities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    内
    0.89
    ians
    0.73
    arna
    0.60
    гура
    0.57
    ध्यक्ष
    0.51
    нан
    0.49
    நாடு
    0.45
    ["
    0.44
    ると
    0.42
    政府
    0.41
    POSITIVE LOGITS
    ities
    2.78
    ITIES
    1.71
    heden
    0.59
    ITY
    0.52
    itys
    0.51
    plasia
    0.50
    ity
    0.48
    idades
    0.47
    alities
    0.46
    ️
    0.44
    Activations Density 0.008%

    No Known Activations