© 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. 206187
    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
    го
    0.89
    ها
    0.86
    що
    0.85
    мым
    0.82
    ذج
    0.82
    да
    0.82
    𝚜
    0.82
    ست
    0.81
    ني
    0.81
    স
    0.80
    POSITIVE LOGITS
    RO
    1.20
    Network
    1.16
    NE
    1.11
    DE
    1.09
    AB
    1.07
     to
    1.05
    NA
    1.05
    RE
    1.00
    ME
    1.00
    RAM
    0.97
    Activations Density 0.000%

    No Known Activations