© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117413
    Prev
    Next
    INDEX
    Explanations

    outer/inner/lower parts

    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_27_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
     сми
    0.18
     chimneys
    0.17
     Schuyler
    0.17
     Churchill
    0.17
    ConnectionString
    0.17
    䅛
    0.17
     readjust
    0.17
    ır
    0.17
     bala
    0.17
     calculation
    0.16
    POSITIVE LOGITS
     parte
    0.18
    ناوی
    0.17
    به
    0.17
    conferences
    0.17
    torio
    0.17
    🔴
    0.16
    $>$
    0.16
    
    0.15
     consiste
    0.15
    محمد
    0.15
    Activations Density 0.005%

    No Known Activations