© 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. 34961
    Prev
    Next
    INDEX
    Explanations

    birth 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_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
    u
    0.82
    un
    0.66
    at
    0.64
     somma
    0.64
    কে
    0.64
    and
    0.63
    urazione
    0.61
    it
    0.61
    ные
    0.61
     sami
    0.61
    POSITIVE LOGITS
    ation
    0.87
    い
    0.75
    २
    0.73
    つい
    0.71
    ни
    0.69
    什么
    0.64
    ح
    0.64
    ை
    0.64
    (),
    0.62
    기
    0.61
    Activations Density 0.031%

    No Known Activations