© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152752
    Prev
    Next
    INDEX
    Explanations

    taking courage and effort

    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_23_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
     захо
    0.38
    図書館
    0.36
     themed
    0.35
     احت
    0.35
    图书馆
    0.35
    本社
    0.34
    みな
    0.34
    踵
    0.34
    VEY
    0.33
     sidelines
    0.33
    POSITIVE LOGITS
     barro
    0.42
     impurity
    0.42
     പരിശ
    0.41
     deuterium
    0.40
    ionante
    0.40
     Steering
    0.39
     bronce
    0.39
    푦
    0.39
     dém
    0.39
    ાદ
    0.39
    Activations Density 0.049%

    No Known Activations