© 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. 10871
    Prev
    Next
    INDEX
    Explanations

    speed of light (c) or mass

    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
     दल
    0.45
     stationary
    0.45
     posizione
    0.40
     Schro
    0.40
     posición
    0.39
    otemporal
    0.39
    藿
    0.38
    stationary
    0.38
     Schrödinger
    0.37
     Partido
    0.37
    POSITIVE LOGITS
     c
    0.45
     gere
    0.40
     Medical
    0.40
     הכ
    0.40
    Medical
    0.39
    фек
    0.39
    eten
    0.38
    जिकल
    0.38
    調節
    0.37
    c
    0.37
    Activations Density 0.072%

    No Known Activations