© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237285
    Prev
    Next
    INDEX
    Explanations

    sweet of you

    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_32_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
     კიდ
    0.45
     READING
    0.45
     ok
    0.44
     OK
    0.42
     okun
    0.39
    ዀ
    0.39
     additionally
    0.38
    modifiers
    0.37
    Ϳ
    0.37
     ಕರ್
    0.37
    POSITIVE LOGITS
    }$,
    0.40
     lemak
    0.39
     lack
    0.37
    ించండి
    0.37
     кислоты
    0.36
    ብር
    0.36
     sweetness
    0.35
     Orthodox
    0.34
    #,
    0.34
     sci
    0.34
    Activations Density 0.002%

    No Known Activations