© 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. 35058
    Prev
    Next
    INDEX
    Explanations

    code technical terms

    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
    @-
    0.38
     '-
    0.38
    _{+}-
    0.37
    ?-
    0.37
    ,-
    0.37
    )–
    0.36
    ሙሉ
    0.35
    —-
    0.34
     অন্ত
    0.34
    ).-
    0.34
    POSITIVE LOGITS
    লেক
    0.42
    (...)
    0.35
    dinga
    0.34
    citenamefont
    0.33
    ifert
    0.33
    ownie
    0.32
    荭
    0.32
    лекса
    0.32
     എന്നിവ
    0.32
    ᱫ
    0.31
    Activations Density 0.033%

    No Known Activations