© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78484
    Prev
    Next
    INDEX
    Explanations

    rephrasing for context and nuance

    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_31_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
     выбора
    0.38
     mengangkat
    0.38
     नामांकन
    0.38
    autocon
    0.37
    躏
    0.37
     АК
    0.37
     consultas
    0.36
     removeItem
    0.36
     blinded
    0.36
     objString
    0.36
    POSITIVE LOGITS
    ibh
    0.38
    ipu
    0.36
    iculares
    0.34
     extra
    0.33
    ims
    0.33
    othi
    0.33
    ・
    0.33
    base
    0.32
     packet
    0.32
    SY
    0.32
    Activations Density 0.022%

    No Known Activations