© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197260
    Prev
    Next
    INDEX
    Explanations

    will take

    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_26_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
     이용
    0.45
    蓯
    0.43
     다양한
    0.42
    KURZ
    0.42
    Reprodu
    0.41
    Cyclone
    0.41
     onClose
    0.41
     reproducibility
    0.40
    ེད་
    0.40
    pubescens
    0.40
    POSITIVE LOGITS
    ’
    0.41
     junto
    0.40
     sopra
    0.39
    ismus
    0.39
    :**
    0.39
     têm
    0.39
    ڃ
    0.39
    4
    0.37
    ឬ
    0.37
    ather
    0.37
    Activations Density 0.000%

    No Known Activations