© 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. 42609
    Prev
    Next
    INDEX
    Explanations

    love at first sight

    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
     Apica
    0.55
     бк
    0.55
     对
    0.54
     гель
    0.52
    堌
    0.52
     стандарт
    0.51
     программ
    0.51
    chdir
    0.51
     মোবাইল
    0.50
     пода
    0.49
    POSITIVE LOGITS
     anxious
    0.58
    К
    0.57
    T
    0.52
     T
    0.51
    別の
    0.51
    X
    0.51
    ﻪ
    0.51
    ultures
    0.50
    ύ
    0.49
     intentions
    0.48
    Activations Density 0.000%

    No Known Activations