© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13065
    Prev
    Next
    INDEX
    Explanations

    ziprecruiter.com

    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_13_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
    LING
    0.54
    rind
    0.54
    緹
    0.54
     Corolle
    0.53
    hur
    0.52
    ermin
    0.52
    umac
    0.52
    ikuti
    0.52
    rif
    0.51
    Mf
    0.51
    POSITIVE LOGITS
    发布
    0.61
    比较
    0.52
     on
    0.51
    وص
    0.49
    São
    0.49
    سون
    0.48
    orsanız
    0.48
     چ
    0.47
    比較
    0.47
    怀孕
    0.47
    Activations Density 0.003%

    No Known Activations