© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202406
    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_46_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
     identifica
    0.42
     confirmation
    0.41
     shipping
    0.41
     shades
    0.41
     ذ
    0.40
    identifiers
    0.39
     SHIPPING
    0.39
    ='')
    0.38
     solids
    0.38
     Osw
    0.38
    POSITIVE LOGITS
    Whilst
    0.41
     whilst
    0.39
    While
    0.39
     Rolling
    0.39
     While
    0.39
     Whilst
    0.38
    Rolling
    0.38
    ulit
    0.37
    袭击
    0.37
     напа
    0.36
    Activations Density 0.000%

    No Known Activations