© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67251
    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_41_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
    クラブ
    0.42
    檴
    0.41
     Украина
    0.40
    櫚
    0.39
     Beruf
    0.39
    CLAMP
    0.38
     klub
    0.38
     lilac
    0.38
    二级
    0.38
    )$\
    0.38
    POSITIVE LOGITS
    Ple
    0.52
    Salt
    0.43
    coal
    0.41
    Bry
    0.41
     Salt
    0.41
    salt
    0.40
     defin
    0.40
    Pressed
    0.39
    割り
    0.39
     दश
    0.39
    Activations Density 0.000%

    No Known Activations