© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167201
    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_31_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
     mustn
    0.50
    CIO
    0.42
    etahui
    0.40
    뗀
    0.40
    ಲ್ಲು
    0.39
     ойнойт
    0.39
     dát
    0.38
    谨慎
    0.38
    忤
    0.38
    mutex
    0.37
    POSITIVE LOGITS
     Regents
    0.39
     Народ
    0.37
     Menc
    0.37
    摄
    0.37
     Ком
    0.36
     Regent
    0.36
     slogan
    0.36
    Accept
    0.36
    相
    0.36
     Góc
    0.35
    Activations Density 0.000%

    No Known Activations