© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 9734
    Prev
    Next
    INDEX
    Explanations

    astype to float32

    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_40_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
    Ago
    0.40
    ैटिन
    0.39
    Ắ
    0.38
     servi
    0.36
     fx
    0.36
    dashed
    0.35
    ከ
    0.35
    пси
    0.35
    kim
    0.35
    김
    0.35
    POSITIVE LOGITS
    䖝
    0.43
     vulnerability
    0.40
     bior
    0.38
     Vulner
    0.37
     OneDrive
    0.37
    蜼
    0.36
     vulnerable
    0.36
     Pto
    0.36
    Normdaten
    0.36
    வேன்
    0.36
    Activations Density 0.016%

    No Known Activations