© 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. 35557
    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
     relay
    0.37
    ወሰ
    0.36
    询
    0.35
     desktop
    0.35
    antoms
    0.34
     relation
    0.34
     vải
    0.34
     Richard
    0.34
     relays
    0.34
     worked
    0.33
    POSITIVE LOGITS
     aktivnosti
    0.34
     VES
    0.34
     Vj
    0.33
    羙
    0.33
    埛
    0.33
    ٣
    0.33
     Ges
    0.32
    ENAME
    0.31
     AMPL
    0.30
    background
    0.30
    Activations Density 0.000%

    No Known Activations