© 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. 8371
    Prev
    Next
    INDEX
    Explanations

    speed numbers and units

    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
     Catering
    0.43
     бра
    0.42
     setzte
    0.40
     cajas
    0.39
     pudd
    0.39
    টিয়
    0.38
    噴
    0.38
     group
    0.38
    მ
    0.37
     setItems
    0.37
    POSITIVE LOGITS
     করিলেন
    0.45
     Hypertension
    0.38
    CHARLES
    0.38
    itched
    0.37
     चर्च
    0.37
    Richard
    0.36
     Superman
    0.36
    archical
    0.36
    Superman
    0.35
     CHARLES
    0.35
    Activations Density 0.007%

    No Known Activations