© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216426
    Prev
    Next
    INDEX
    Explanations

    cooling and promptness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     воспа
    0.45
    mT
    0.39
     Botany
    0.39
     Escape
    0.38
     promoc
    0.38
    畿
    0.38
     CAB
    0.38
    rafpunkte
    0.37
     cellular
    0.36
    कृपया
    0.36
    POSITIVE LOGITS
     ತಿಳ
    0.38
    审计
    0.38
    オブ
    0.37
    白
    0.37
    安倍
    0.37
     Owners
    0.36
     forklift
    0.36
     vulnerabilities
    0.36
    ச்சல்
    0.35
    prüfung
    0.35
    Activations Density 0.003%

    No Known Activations