© 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. 201536
    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
     соц
    0.44
     Auk
    0.39
     Krak
    0.38
    脣
    0.38
    Lip
    0.38
     тон
    0.38
    லர்
    0.38
    竻
    0.37
    䒠
    0.37
    BAS
    0.37
    POSITIVE LOGITS
    FormBorderStyle
    0.38
    markets
    0.37
    stock
    0.37
     stock
    0.36
     Foot
    0.36
     compromise
    0.35
    дию
    0.35
    streets
    0.35
     Streets
    0.34
    Foot
    0.34
    Activations Density 0.000%

    No Known Activations