© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245677
    Prev
    Next
    INDEX
    Explanations

    to-do list app

    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_40_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
    rivate
    0.42
    ostino
    0.40
    ettings
    0.39
    খানি
    0.39
     ahorrar
    0.38
    㛺
    0.37
     práci
    0.37
    μί
    0.37
    宒
    0.37
    工作的
    0.36
    POSITIVE LOGITS
     মুঠ
    0.41
     bon
    0.40
    <=>
    0.39
    üman
    0.38
    
    0.37
    pattern
    0.37
     crowns
    0.37
    izi
    0.37
    fg
    0.37
     Shields
    0.36
    Activations Density 0.002%

    No Known Activations