© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92801
    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_11_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
    ﺪ
    0.56
     ganhar
    0.54
     hypotheses
    0.54
     phytochemical
    0.53
     estabilidad
    0.52
     derecha
    0.50
     química
    0.49
     να
    0.48
     sezione
    0.47
     chuck
    0.47
    POSITIVE LOGITS
    ए
    0.53
    length
    0.52
    Lä
    0.52
    ل
    0.52
    Len
    0.48
    per
    0.47
    bec
    0.47
    Transportation
    0.47
     or
    0.46
    et
    0.46
    Activations Density 0.000%

    No Known Activations