© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133632
    Prev
    Next
    INDEX
    Explanations

    f followed by common substrings

    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_1_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
     a
    1.13
    ↵
    1.02
    嶆
    0.99
    $,
    0.98
     colet
    0.95
    诩
    0.86
    aloo
    0.86
     u
    0.85
    ↵↵
    0.85
     gente
    0.85
    POSITIVE LOGITS
    of
    1.56
    น
    1.45
    s
    1.39
    지에
    1.22
    ्या
    1.20
    し
    1.19
    의
    1.18
    se
    1.16
    m
    1.16
    dan
    1.14
    Activations Density 0.001%

    No Known Activations