© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246764
    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_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
    校验
    0.44
    xcsche
    0.40
     validates
    0.39
     রাজ্য
    0.38
     validation
    0.36
     überprü
    0.36
    aniline
    0.36
    扳
    0.36
    ляет
    0.35
     validating
    0.35
    POSITIVE LOGITS
     SNS
    0.42
    twitter
    0.41
     sos
    0.39
     beaux
    0.38
     jub
    0.38
    SNS
    0.37
     جميل
    0.37
     SOS
    0.36
    logan
    0.36
     nucle
    0.36
    Activations Density 0.001%

    No Known Activations