© 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. 34502
    Prev
    Next
    INDEX
    Explanations

    formality level

    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
     позволя
    0.31
     wel
    0.30
     compliance
    0.30
     rans
    0.30
     destrucción
    0.30
    )^{*}$
    0.30
     свойства
    0.29
    逞
    0.28
     fi
    0.28
    compliance
    0.28
    POSITIVE LOGITS
     डिप्ट
    0.29
    NEED
    0.29
    }=(\
    0.28
    Pen
    0.28
     بغیر
    0.28
    原则
    0.28
    配备
    0.28
    ıyor
    0.28
     مين
    0.28
    ponsored
    0.27
    Activations Density 0.021%

    No Known Activations