© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24597
    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_10_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
    log
    0.52
    ’
    0.52
    alla
    0.49
     .
    0.49
    ther
    0.48
    her
    0.48
    ্নার
    0.47
    erc
    0.47
    thers
    0.47
     Der
    0.47
    POSITIVE LOGITS
    Ᏸ
    0.64
    ра
    0.61
    тан
    0.58
    в
    0.56
     acidente
    0.54
     crescita
    0.53
     associée
    0.53
    ريقه
    0.52
    ранже
    0.52
     автобу
    0.51
    Activations Density 0.000%

    No Known Activations