© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82614
    Prev
    Next
    INDEX
    Explanations

    fashion and rugged

    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_0_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
    of
    1.62
     terminado
    1.25
    る
    1.25
    ﻑ
    1.20
     for
    1.18
    。「
    1.18
     примене
    1.17
     dezvolt
    1.15
    erweise
    1.14
     դ
    1.13
    POSITIVE LOGITS
    1
    2.14
    v
    1.95
    il
    1.85
    ва
    1.84
    n
    1.70
    ir
    1.64
    b
    1.58
    ни
    1.52
    an
    1.46
    нено
    1.46
    Activations Density 0.000%

    No Known Activations