© 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. 123206
    Prev
    Next
    INDEX
    Explanations

    swimlanes or lanes

    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
    1
    0.73
    analyse
    0.68
    يز
    0.67
    th
    0.66
    stro
    0.64
    7
    0.64
    us
    0.63
    ginx
    0.63
    bö
    0.62
    newlines
    0.62
    POSITIVE LOGITS
    a
    0.89
    の
    0.85
    ה
    0.82
    ን
    0.79
     sworn
    0.77
     ancienne
    0.77
     ב
    0.75
    의
    0.75
     ν
    0.75
     וא
    0.73
    Activations Density 0.000%

    No Known Activations