© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258416
    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_22_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
    ش
    0.58
    ש
    0.56
     comprob
    0.55
    ില
    0.52
     cocina
    0.50
     oxidación
    0.50
    zinha
    0.49
     পাঁচ
    0.48
     iunie
    0.48
    م
    0.48
    POSITIVE LOGITS
     lawful
    0.48
     future
    0.46
     Legit
    0.43
     Stelle
    0.42
     peace
    0.41
     Explos
    0.40
     Australia
    0.40
     verloren
    0.40
     Великой
    0.40
     nail
    0.40
    Activations Density 0.000%

    No Known Activations