© 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. 207582
    Prev
    Next
    INDEX
    Explanations

    feed

    np_max-act-logits · gemini-2.5-flash-lite
    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
     E
    1.57
    E
    1.42
     eat
    1.33
     eats
    1.29
     е
    1.28
     eaten
    1.23
     Eat
    1.18
    Eat
    1.17
     Eaton
    1.16
     e
    1.14
    POSITIVE LOGITS
     feeding
    0.57
     feed
    0.53
    Feeding
    0.52
     Feeding
    0.50
     feeds
    0.49
    feed
    0.46
    feeding
    0.44
    feeds
    0.41
    Feed
    0.41
     Feed
    0.41
    Activations Density 0.001%

    No Known Activations