© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196830
    Prev
    Next
    INDEX
    Explanations

    Junk

    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_50_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
     prairie
    0.43
    PRA
    0.41
    pra
    0.41
    FG
    0.41
     Pra
    0.39
     Jac
    0.38
    PPTV
    0.38
     F
    0.38
     pra
    0.38
    ktron
    0.37
    POSITIVE LOGITS
     lega
    0.45
    ylmethyl
    0.39
    achusetts
    0.38
    াবের
    0.38
     যোদ্ধ
    0.38
     карда
    0.38
    ョ
    0.38
    vindo
    0.37
    鶘
    0.36
    ુલ
    0.35
    Activations Density 0.000%

    No Known Activations