© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147090
    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_59_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
    abhas
    0.43
     یخ
    0.39
    ล็
    0.38
    ത്വം
    0.38
    ishable
    0.37
    ندہ
    0.37
    锁
    0.36
     ए
    0.36
     ?”
    0.36
    ende
    0.36
    POSITIVE LOGITS
    Most
    0.44
     most
    0.43
    ֡
    0.40
     sharpness
    0.35
     hexa
    0.35
    ```
    0.34
     totam
    0.34
    0.34
    ·
    0.33
    most
    0.33
    Activations Density 0.000%

    No Known Activations