© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4447
    Prev
    Next
    INDEX
    Explanations

    function parameters

    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_39_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
     Vaill
    0.38
     epoxide
    0.37
    铱
    0.37
    䧼
    0.37
     Activ
    0.37
     Diffusion
    0.37
    िरा
    0.36
     ttk
    0.36
     Starr
    0.36
    Референ
    0.36
    POSITIVE LOGITS
    param
    0.46
     XXI
    0.37
     param
    0.36
    över
    0.35
     χει
    0.34
    |\
    0.34
    |+\
    0.33
    ÍT
    0.33
     XXV
    0.33
    ⌋
    0.33
    Activations Density 0.003%

    No Known Activations