© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192661
    Prev
    Next
    INDEX
    Explanations

    Lobelia or Sobel operators

    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_4_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
    in
    1.42
    er
    1.38
    ens
    1.30
    é
    1.27
    ater
    1.27
    ess
    1.24
    ade
    1.23
    ik
    1.17
    im
    1.16
    ER
    1.14
    POSITIVE LOGITS
    。
    1.13
    ૫
    0.99
    ᱖
    0.93
     Nói
    0.91
    ٥
    0.89
    시
    0.87
     ناحيه
    0.87
    ｱ
    0.86
    ﾁ
    0.86
     ولوبی
    0.85
    Activations Density 0.001%

    No Known Activations