© 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. 200617
    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
    ید
    1.08
    िया
    0.99
    ний
    0.92
    νο
    0.92
    ssä
    0.91
    ून
    0.88
    ف
    0.85
    ниях
    0.84
    ری
    0.84
    ால்
    0.83
    POSITIVE LOGITS
    el
    1.28
    kunst
    1.05
     servizi
    1.02
    л
    1.00
    w
    0.98
    et
    0.97
    le
    0.97
    يه
    0.96
    يد
    0.96
     kleine
    0.95
    Activations Density 0.000%

    No Known Activations