© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178588
    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_24_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
     expt
    0.40
     pessoal
    0.39
    árl
    0.38
     destes
    0.37
    Personally
    0.36
     lé
    0.36
    deserved
    0.36
    Ꭳ
    0.36
    ghi
    0.35
     Wembley
    0.35
    POSITIVE LOGITS
     вже
    0.43
    ᚖ
    0.37
    த்ரே
    0.36
     Thunder
    0.35
     Hood
    0.35
    дання
    0.35
     ancient
    0.34
     envisioned
    0.34
    খানে
    0.33
     כבר
    0.33
    Activations Density 0.000%

    No Known Activations