© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248625
    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_56_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
     bothering
    0.44
    â
    0.38
     bother
    0.38
     document
    0.38
     bothers
    0.38
    document
    0.37
    olé
    0.37
    äk
    0.36
     थियो
    0.36
     th
    0.35
    POSITIVE LOGITS
    既
    0.37
    urangi
    0.35
     압
    0.35
    цна
    0.35
     tosses
    0.35
    ცია
    0.34
    could
    0.34
    uginosa
    0.33
     could
    0.33
    wax
    0.33
    Activations Density 0.000%

    No Known Activations