© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100351
    Prev
    Next
    INDEX
    Explanations

    text extraction

    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_14_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
     hierarchies
    0.50
    skew
    0.50
    ArrowToggle
    0.49
     dissati
    0.48
    >\<^
    0.48
    λοι
    0.48
    $&$-
    0.48
    sdale
    0.47
    єте
    0.46
    FlashValue
    0.46
    POSITIVE LOGITS
    O
    0.55
    無法
    0.51
     dit
    0.50
     potter
    0.49
    ¡
    0.48
     Scholar
    0.47
     Méd
    0.47
    Mét
    0.47
     Pin
    0.46
     Library
    0.46
    Activations Density 0.000%

    No Known Activations