© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239554
    Prev
    Next
    INDEX
    Explanations

    bold, highlighted, first, version

    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_25_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
    acchar
    0.34
    SCIENCE
    0.32
    मती
    0.31
    捷
    0.31
     Anleitung
    0.31
     Поэтому
    0.31
     floribus
    0.31
    Notwithstanding
    0.30
    ydia
    0.30
    徳
    0.30
    POSITIVE LOGITS
     Daily
    0.33
     Purdue
    0.33
     '':
    0.32
     daily
    0.32
     Brie
    0.31
     Roman
    0.31
     hardest
    0.31
     Figure
    0.31
    ncol
    0.31
     demon
    0.30
    Activations Density 0.014%

    No Known Activations