© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14831
    Prev
    Next
    INDEX
    Explanations

    SQL table definition keywords

    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_40_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
     Brewery
    0.37
    <0x88>
    0.37
    倠
    0.37
    攽
    0.37
    خصص
    0.36
     Timm
    0.36
     Monsanto
    0.35
    笂
    0.35
     Leach
    0.34
    Brewer
    0.34
    POSITIVE LOGITS
    佗
    0.38
     playerId
    0.38
     ciudadano
    0.36
    bahnhof
    0.36
     मातरम
    0.35
     ENVIRONMENTAL
    0.35
     until
    0.34
     audioEngine
    0.34
     ridiculous
    0.34
     جما
    0.34
    Activations Density 0.001%

    No Known Activations