© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60035
    Prev
    Next
    INDEX
    Explanations

    company

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     musical
    0.61
    musical
    0.50
    Ꮔ
    0.43
     Phantom
    0.42
    Musical
    0.41
     Musical
    0.41
     phantom
    0.40
     陈
    0.39
     ACCEPT
    0.39
     Anita
    0.38
    POSITIVE LOGITS
     company
    0.70
    company
    0.70
    Company
    0.68
     Company
    0.66
     कंपनी
    0.63
     şirk
    0.62
    News
    0.57
     компания
    0.55
     کمپنی
    0.54
     કંપની
    0.54
    Activations Density 0.000%

    No Known Activations