© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91307
    Prev
    Next
    INDEX
    Explanations

    Pyxis, CUDA, audio, Robin Sequence

    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_3_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
    ق
    0.89
    ק
    0.73
    inin
    0.65
    ﹁
    0.60
    لی
    0.59
    ین
    0.58
    angnya
    0.58
    '،
    0.58
    ری
    0.57
    EtOH
    0.56
    POSITIVE LOGITS
     cí
    0.57
    s
    0.56
    с
    0.56
     موسي
    0.56
     servitude
    0.55
     ==
    0.54
    ně
    0.54
     ktorý
    0.54
    ни
    0.54
     vies
    0.54
    Activations Density 0.003%

    No Known Activations