© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18783
    Prev
    Next
    INDEX
    Explanations

    I followed by verb

    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_15_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
    0.51
     to
    0.49
     admissibility
    0.48
    s
    0.48
     inaccurate
    0.48
     inhab
    0.48
     undue
    0.47
     are
    0.45
     manc
    0.45
     timp
    0.45
    POSITIVE LOGITS
     лучших
    0.45
     самых
    0.43
    种类
    0.42
    विक
    0.42
    ACIÓN
    0.42
    літы
    0.41
    áról
    0.41
    逍
    0.40
    ूल
    0.40
     更新
    0.40
    Activations Density 0.011%

    No Known Activations