© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11324
    Prev
    Next
    INDEX
    Explanations

    qualified professionals and roles

    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_13_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
    <0xA6>
    0.48
     bowed
    0.45
     бө
    0.43
     건
    0.42
     휴대
    0.42
     corrente
    0.42
     dragonfly
    0.41
     Pologne
    0.39
    冨
    0.39
     ترک
    0.39
    POSITIVE LOGITS
     Scientists
    0.47
    嬿
    0.47
     grads
    0.46
    াকা
    0.46
     Cooley
    0.45
     laurea
    0.45
    chos
    0.44
     theses
    0.44
     Science
    0.44
    acionales
    0.43
    Activations Density 0.034%

    No Known Activations