© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148712
    Prev
    Next
    INDEX
    Explanations

    Linux package managers

    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_23_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
     truncate
    0.43
    ,’
    0.37
    ኔ
    0.37
    ersburg
    0.37
    展開
    0.37
     capitalize
    0.37
     Bootcamp
    0.37
    fill
    0.35
     xrd
    0.35
    Susan
    0.35
    POSITIVE LOGITS
     adatto
    0.43
     sotto
    0.40
    alve
    0.40
    菒
    0.40
    蕗
    0.40
    姮
    0.40
     serviço
    0.40
     şeyler
    0.40
     możliwość
    0.39
    这话
    0.39
    Activations Density 0.000%

    No Known Activations