© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176515
    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_24_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
    菈
    0.44
     नामक
    0.43
     Serious
    0.43
     Cube
    0.41
     to
    0.41
     mask
    0.41
     गंभीर
    0.39
     Detective
    0.39
    වුන්
    0.39
     Scare
    0.39
    POSITIVE LOGITS
     stejně
    0.52
    advised
    0.52
    b
    0.50
    recorded
    0.49
     ceded
    0.49
     subordinates
    0.47
    なかった
    0.46
    Unser
    0.46
     discre
    0.45
    written
    0.45
    Activations Density 0.000%

    No Known Activations