© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17431
    Prev
    Next
    INDEX
    Explanations

    first teeth or what do you call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    Radial
    0.53
     radial
    0.49
     radius
    0.46
     Radial
    0.46
     r
    0.42
    radius
    0.41
    agram
    0.41
    Kia
    0.40
    radial
    0.40
     repatri
    0.39
    POSITIVE LOGITS
     feed
    0.51
     playtime
    0.49
     play
    0.46
     Feed
    0.46
    feed
    0.45
     Walking
    0.44
     walkers
    0.44
    玩
    0.43
     걸
    0.43
     twisting
    0.43
    Activations Density 0.071%

    No Known Activations