© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152632
    Prev
    Next
    INDEX
    Explanations

    fever

    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_23_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
     харак
    0.38
     আগের
    0.37
    剻
    0.37
     בית
    0.36
    ٹن
    0.35
    Disposition
    0.35
    ウト
    0.35
    ńskim
    0.35
    执
    0.34
    zków
    0.34
    POSITIVE LOGITS
    osin
    0.47
     peptides
    0.43
     awe
    0.41
    pixels
    0.39
     jung
    0.39
     particles
    0.38
     වීම
    0.38
    ppings
    0.38
     calligraphy
    0.38
     отлич
    0.38
    Activations Density 0.002%

    No Known Activations