© 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. 253696
    Prev
    Next
    INDEX
    Explanations

    say "{"

    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
     gonna
    0.53
     wanna
    0.50
     outta
    0.44
     multi
    0.40
     Gonna
    0.39
    啱
    0.39
     Wanna
    0.37
     کنه
    0.35
    oció
    0.35
     rocker
    0.34
    POSITIVE LOGITS
    INAL
    0.41
    inal
    0.40
    Hus
    0.37
    dog
    0.36
    Brexit
    0.35
     http
    0.35
    Dog
    0.35
     HashTable
    0.34
     Zoll
    0.34
    ↡
    0.34
    Activations Density 0.000%

    No Known Activations