© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178180
    Prev
    Next
    INDEX
    Explanations

    setting the scene for adventures

    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_24_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
     ሆ
    0.40
     ለ
    0.38
    大な
    0.37
    emaakt
    0.36
     upheaval
    0.36
    Hotkey
    0.36
    deployRoot
    0.35
     няко
    0.35
    ホ
    0.35
    frameN
    0.35
    POSITIVE LOGITS
     miscellaneous
    0.38
     নীতি
    0.38
     xt
    0.38
     "&
    0.37
    ictures
    0.37
    atanam
    0.37
     Condiciones
    0.37
     pong
    0.36
    kath
    0.36
     dave
    0.36
    Activations Density 0.014%

    No Known Activations