© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178967
    Prev
    Next
    INDEX
    Explanations

    analytic verbs and actions

    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_29_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
     verloren
    0.45
    är
    0.45
    აფ
    0.42
     umož
    0.42
    эр
    0.39
    ایید
    0.37
    łop
    0.37
    ܀
    0.37
     gesch
    0.37
    凖
    0.36
    POSITIVE LOGITS
    Filled
    0.41
     विद्रोह
    0.40
     morales
    0.40
     intercourse
    0.39
     घ्यावी
    0.39
     চেষ্টা
    0.38
     setName
    0.38
    Soap
    0.37
     progresses
    0.37
     coba
    0.36
    Activations Density 0.001%

    No Known Activations