© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175846
    Prev
    Next
    INDEX
    Explanations

    tempo and threshold running paces

    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_20_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
    परेशन
    0.49
     midwives
    0.47
     |,
    0.46
     variabile
    0.46
    流程
    0.46
     hof
    0.46
     cooperación
    0.46
     travellers
    0.45
    nivel
    0.45
    sistema
    0.44
    POSITIVE LOGITS
     Knowles
    0.49
     Reading
    0.47
     Davis
    0.43
     ST
    0.43
     ሊ
    0.42
     Voraussetzungen
    0.42
     U
    0.41
    EndY
    0.41
     दशक
    0.41
     late
    0.40
    Activations Density 0.003%

    No Known Activations