© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80625
    Prev
    Next
    INDEX
    Explanations

    in short, in conclusion, in essence

    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_29_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
     फायदे
    0.42
     Markt
    0.41
     ❤️
    0.40
     SupCt
    0.40
     ❤
    0.40
     😍
    0.39
     Ich
    0.39
     Big
    0.38
     Bab
    0.38
    bab
    0.38
    POSITIVE LOGITS
     сведения
    0.41
    мма
    0.40
     decently
    0.40
     alchemy
    0.39
    剞
    0.38
     nisid
    0.38
     evolved
    0.37
    μως
    0.37
     pesky
    0.37
     postaci
    0.36
    Activations Density 0.001%

    No Known Activations