© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    starting from scratch

    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
    ใหม่
    0.10
    gia
    0.09
    SError
    0.09
     最初
    0.09
    图像
    0.09
    p
    0.09
    hbs
    0.09
    com
    0.09
    з
    0.09
     editing
    0.09
    POSITIVE LOGITS
     চমৎকার
    0.11
     chairman
    0.10
    excellent
    0.10
     colnames
    0.10
    outstanding
    0.10
     Dewar
    0.09
     Devon
    0.09
    attractive
    0.09
    )”.
    0.09
     ры
    0.09
    Activations Density 0.020%

    No Known Activations