© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30701
    Prev
    Next
    INDEX
    Explanations

    kotlin extensions and runtime

    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_40_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
    ﺫ
    0.40
     protections
    0.39
    kish
    0.39
     Feldman
    0.39
     используется
    0.39
    表现
    0.38
    riture
    0.38
     mapped
    0.38
     Constitution
    0.37
     besitzt
    0.36
    POSITIVE LOGITS
     hipert
    0.40
    ୁ
    0.38
    シー
    0.38
    arc
    0.37
     Arc
    0.37
    十字
    0.37
    Arc
    0.36
     plaster
    0.36
    häng
    0.36
     despert
    0.36
    Activations Density 0.002%

    No Known Activations