© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80350
    Prev
    Next
    INDEX
    Explanations

    tell me what to do

    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
    Ñ
    0.37
    不允许
    0.36
    Existe
    0.36
    큥
    0.36
    ieson
    0.35
    视频
    0.35
     биологи
    0.35
     Immunol
    0.35
    radle
    0.34
    мна
    0.34
    POSITIVE LOGITS
    萜
    0.42
    Setting
    0.37
     Setting
    0.36
    ポケット
    0.36
    Hang
    0.35
    potent
    0.35
    Vert
    0.34
    ceral
    0.34
     mengatur
    0.34
    چ
    0.34
    Activations Density 0.004%

    No Known Activations