© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198517
    Prev
    Next
    INDEX
    Explanations

    bike

    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_50_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
    uese
    0.41
    샅
    0.40
     pyrr
    0.40
     pf
    0.39
    äss
    0.37
     Quarry
    0.37
     Fallon
    0.37
     quarry
    0.36
    옻
    0.36
    த்ய
    0.35
    POSITIVE LOGITS
     bic
    2.52
     bike
    2.34
    Bike
    2.28
     Bic
    2.28
     bik
    2.27
     Bike
    2.23
     BIC
    2.23
     Bik
    2.20
    bic
    2.16
    bike
    2.13
    Activations Density 0.003%

    No Known Activations