© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208878
    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_25_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
    ：（
    0.52
     pirm
    0.49
    +'.
    0.47
     আসতে
    0.47
     emargin
    0.46
     Sonya
    0.46
    :'#
    0.44
     ciclo
    0.44
     শন
    0.44
    তুন
    0.43
    POSITIVE LOGITS
     Ramsay
    0.43
     Entrance
    0.42
    bibliothek
    0.40
     }
    0.40
     கன
    0.40
     Rush
    0.39
     Writings
    0.39
     Recordings
    0.39
    சாலை
    0.39
    us
    0.38
    Activations Density 0.000%

    No Known Activations