© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103568
    Prev
    Next
    INDEX
    Explanations

    фантастика, интернет, филе

    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_1_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
    洳
    1.05
    攺
    1.00
    مه
    0.98
     in
    0.96
     svært
    0.93
     lucha
    0.92
     és
    0.92
    訛
    0.91
    淉
    0.90
    見
    0.89
    POSITIVE LOGITS
    '
    2.14
    ت
    2.03
    ي
    1.78
    т
    1.62
    .
    1.60
    ה
    1.59
    м
    1.53
    ი
    1.51
    .'
    1.48
    י
    1.46
    Activations Density 0.000%

    No Known Activations