© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195915
    Prev
    Next
    INDEX
    Explanations

    emphasis punctuation

    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
     identification
    0.39
     Woot
    0.38
     Spain
    0.37
     anyhow
    0.37
    の実
    0.36
    曽
    0.35
     st
    0.35
     escaped
    0.35
    0.35
     France
    0.34
    POSITIVE LOGITS
     Mond
    0.42
    obr
    0.42
    ဒီ
    0.39
    GetLastError
    0.39
     EIS
    0.39
     EFL
    0.39
    𝗟
    0.39
    CSR
    0.39
    蒙
    0.38
    嚩
    0.38
    Activations Density 0.000%

    No Known Activations