© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13630
    Prev
    Next
    INDEX
    Explanations

    going for

    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_13_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
    ว
    0.52
    w
    0.50
    йн
    0.49
    ไม่มี
    0.49
    г
    0.46
    as
    0.44
     krv
    0.43
    ad
    0.43
    ทุก
    0.43
     transporte
    0.42
    POSITIVE LOGITS
    学校
    0.50
    chard
    0.48
     località
    0.46
     नसी
    0.45
    Datos
    0.44
    InnoDB
    0.44
    edos
    0.43
    łac
    0.43
    ケ
    0.43
    Doctors
    0.43
    Activations Density 0.018%

    No Known Activations