© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28940
    Prev
    Next
    INDEX
    Explanations

    after that,

    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_10_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
    1.15
    т
    0.73
    𝘁
    0.70
    ತ
    0.67
    tte
    0.66
    𝚝
    0.66
    től
    0.65
    <0x9A>
    0.64
    ьте
    0.63
    тов
    0.63
    POSITIVE LOGITS
    8
    0.76
    0
    0.74
    4
    0.71
    DI
    0.68
    Kindly
    0.68
    .",
    0.68
     at
    0.68
    U
    0.67
    RNA
    0.66
    LO
    0.66
    Activations Density 0.005%

    No Known Activations