© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57345
    Prev
    Next
    INDEX
    Explanations

    "explained" followed by punctuation or explanatory details

    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_11_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
     byly
    0.59
     సై
    0.55
    were
    0.54
    for
    0.54
     [];
    0.52
    ផុត
    0.52
    ㄵ
    0.51
    劷
    0.51
    proton
    0.50
    휠
    0.50
    POSITIVE LOGITS
    -
    0.70
    ر
    0.51
    ین
    0.49
     sensibilities
    0.48
    -*
    0.48
    াবে
    0.48
    ه‌
    0.48
     earnest
    0.48
     आसपास
    0.47
     edgy
    0.47
    Activations Density 0.003%

    No Known Activations