© 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. 162333
    Prev
    Next
    INDEX
    Explanations

    it's true that

    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
    >):
    0.38
     ठ
    0.35
    بول
    0.35
     Blink
    0.35
    бол
    0.34
     Ackerman
    0.34
     nomenclature
    0.34
     бол
    0.33
     PUBL
    0.33
     برخور
    0.33
    POSITIVE LOGITS
    ጊዜ
    0.40
     टाइगर
    0.40
     બનાવ
    0.39
     виконання
    0.38
    ʘ
    0.38
     جبکہ
    0.38
    Seine
    0.37
     Seine
    0.37
     légales
    0.37
    oração
    0.36
    Activations Density 0.002%

    No Known Activations