© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213080
    Prev
    Next
    INDEX
    Explanations

    individuals

    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_43_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
     Ranges
    0.37
    $-[
    0.37
    가
    0.37
    ／
    0.37
     superst
    0.36
    handlungen
    0.36
    hitth
    0.36
    τας
    0.36
     पॉलिटिकल
    0.35
    DialogWhen
    0.35
    POSITIVE LOGITS
    icin
    0.43
    致
    0.39
     scler
    0.37
    methylene
    0.37
     Babcock
    0.36
    暝
    0.36
    jot
    0.36
     graham
    0.35
    gleichen
    0.35
    abilecek
    0.34
    Activations Density 0.001%

    No Known Activations