© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231691
    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_6_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
     can
    1.05
    е
    1.00
    یم
    0.96
     akan
    0.92
    о
    0.91
     are
    0.89
    ä
    0.88
    ի
    0.85
    ʻ
    0.81
     حتی
    0.81
    POSITIVE LOGITS
    től
    0.93
    و
    0.87
    dj
    0.86
    dong
    0.84
    dür
    0.80
    2
    0.80
    tól
    0.78
    nich
    0.75
    nél
    0.75
    dq
    0.74
    Activations Density 0.000%

    No Known Activations