© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136438
    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_12_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
     atrap
    0.55
     বউ
    0.55
     cưới
    0.55
     an
    0.53
    laszt
    0.53
     nervioso
    0.53
     डन
    0.52
    䙲
    0.52
    IVIDUAL
    0.52
     തയ്യാ
    0.51
    POSITIVE LOGITS
    og
    0.71
    z
    0.68
    r
    0.64
    ou
    0.63
    at
    0.60
    ow
    0.56
    ul
    0.56
    р
    0.56
    with
    0.55
    o
    0.55
    Activations Density 0.000%

    No Known Activations