© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118139
    Prev
    Next
    INDEX
    Explanations

    Roman numeral II or III headings

    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_27_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
    足
    0.38
    Cookies
    0.37
     gotten
    0.35
    вър
    0.34
     Renn
    0.34
     ale
    0.34
    কি
    0.34
    endosi
    0.34
    Denn
    0.34
    от
    0.33
    POSITIVE LOGITS
     นิด
    0.45
    ingar
    0.40
     República
    0.38
    瑤
    0.37
    排放
    0.36
     defaults
    0.36
     COUNTY
    0.35
    elio
    0.35
     ಮಾಡಲು
    0.35
    olver
    0.35
    Activations Density 0.006%

    No Known Activations