© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59148
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    o
    0.69
    は
    0.65
    是
    0.58
    는
    0.58
    ۔
    0.57
    d
    0.56
    ao
    0.55
    ના
    0.54
    one
    0.53
    for
    0.53
    POSITIVE LOGITS
    к
    0.66
    л
    0.56
    ש
    0.50
    ?
    0.46
     Identifier
    0.45
    大
    0.44
    );}
    0.42
    ت
    0.42
    Yi
    0.41
     Reproduced
    0.41
    Activations Density 0.000%

    No Known Activations