© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207404
    Prev
    Next
    INDEX
    Explanations

    company names and associated products

    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_19_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
     Виктор
    0.35
     Comics
    0.35
     एजेंसियों
    0.34
     DMC
    0.34
    사
    0.34
     लिए
    0.34
     पुणे
    0.34
    वाड़ी
    0.34
     сцене
    0.34
    वीर
    0.33
    POSITIVE LOGITS
     resultante
    0.34
     comte
    0.33
     delim
    0.33
     indigo
    0.33
     nonchal
    0.33
    듬
    0.32
     consul
    0.32
     centralization
    0.32
     lebens
    0.32
     ئێ
    0.32
    Activations Density 0.010%

    No Known Activations