© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178519
    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_24_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
     プラス
    0.50
    Mari
    0.45
     bav
    0.45
     περισσότε
    0.44
    ♥️
    0.44
    ANCE
    0.43
     )))
    0.43
     🥰
    0.42
    ㄅ
    0.42
    墘
    0.42
    POSITIVE LOGITS
     giả
    0.51
     revoke
    0.41
    steller
    0.41
    ര്‍ന്ന്
    0.41
    getInt
    0.41
    胆
    0.40
     violência
    0.40
     müz
    0.39
     denounce
    0.39
     nghiêm
    0.39
    Activations Density 0.000%

    No Known Activations