© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149415
    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_23_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
    ოს
    0.44
     وقف
    0.44
     в
    0.44
     かわいい
    0.43
    壊
    0.43
     déc
    0.43
    โดย
    0.42
     имат
    0.42
    ুপ্ত
    0.42
    ınca
    0.42
    POSITIVE LOGITS
     benöt
    0.45
     Verständ
    0.41
    ㄍ
    0.41
     pohon
    0.41
    解决方法
    0.40
     nöt
    0.39
    Перед
    0.39
    товая
    0.39
     இடத்தில்
    0.39
     gejala
    0.39
    Activations Density 0.000%

    No Known Activations