© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213582
    Prev
    Next
    INDEX
    Explanations

    specific identifiers/fragments

    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_50_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
    setContentType
    0.47
     nonconvex
    0.39
    cir
    0.38
    gradient
    0.37
    콥
    0.37
    rapolation
    0.37
    蠱
    0.37
     па
    0.36
     Paula
    0.36
    cuda
    0.36
    POSITIVE LOGITS
    azón
    0.39
    ashi
    0.39
    ເຊ
    0.38
    اشی
    0.37
     Moh
    0.37
    絶縁
    0.37
    فون
    0.36
    Hil
    0.36
    เซล
    0.36
     Yarm
    0.36
    Activations Density 0.007%

    No Known Activations