© 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
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    $>$
    0.44
    ถุนายน
    0.42
    getBoolean
    0.39
    isRequired
    0.38
    datatype
    0.37
    yticks
    0.37
     misconception
    0.37
    cares
    0.36
     kaj
    0.36
    と思った
    0.36
    POSITIVE LOGITS
     raíz
    0.41
    㖷
    0.41
     wen
    0.39
     começ
    0.39
     έχει
    0.39
     líder
    0.38
     má
    0.38
     vane
    0.38
    大致
    0.38
     ξεκ
    0.38
    Activations Density 0.000%

    No Known Activations