© 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. 216528
    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
     inhibitory
    0.37
     Ú
    0.36
    ací
    0.36
     Proble
    0.35
     انگ
    0.34
     Czechoslovak
    0.34
     অ্যাক
    0.34
     ನಿರ್
    0.34
    keletal
    0.34
     장애
    0.33
    POSITIVE LOGITS
     dete
    0.38
    𝓹
    0.38
     discovering
    0.36
    DET
    0.36
    resto
    0.36
    兟
    0.36
    ؟.
    0.35
    discover
    0.35
     varphi
    0.34
    candidate
    0.34
    Activations Density 0.000%

    No Known Activations