© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34042
    Prev
    Next
    INDEX
    Explanations

    key, value, or assignment separators

    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
    unoscut
    0.36
    тоў
    0.35
    ൺ
    0.35
     perspect
    0.33
    ---+
    0.33
     ВК
    0.33
     ဖြစ်
    0.32
     Erste
    0.32
     arbejde
    0.32
    unkte
    0.31
    POSITIVE LOGITS
    0.34
    迫
    0.33
    smittel
    0.33
                                   
    0.32
    лили
    0.32
    ني
    0.32
     તમને
    0.32
    弥
    0.32
    🖇
    0.31
    ্রাস
    0.31
    Activations Density 0.108%

    No Known Activations