© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217124
    Prev
    Next
    INDEX
    Explanations

    override fun

    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_16_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
    hensive
    0.58
    т
    0.55
     Insulation
    0.55
    絶縁
    0.54
     incomparable
    0.52
     stead
    0.52
     कवच
    0.52
    vection
    0.51
     disguise
    0.50
     verlassen
    0.50
    POSITIVE LOGITS
    íti
    0.56
    í
    0.56
    ice
    0.53
    ige
    0.49
    ny
    0.49
     μόνο
    0.49
    ího
    0.49
    iemi
    0.48
     **
    0.47
    gó
    0.47
    Activations Density 0.000%

    No Known Activations