© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44235
    Prev
    Next
    INDEX
    Explanations

    traverse, journey, descent, navigation

    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_13_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
     an
    0.61
    рт
    0.57
    bot
    0.57
    DET
    0.53
    _|
    0.51
    دول
    0.50
    дят
    0.50
    بك
    0.49
    !)
    0.49
    вли
    0.49
    POSITIVE LOGITS
     pengetahuan
    0.56
     গা
    0.54
     dependences
    0.53
    ⵎ
    0.53
     integra
    0.53
    ସ
    0.53
    enya
    0.52
     زیرمه
    0.51
     pengguna
    0.51
    aren
    0.50
    Activations Density 0.032%

    No Known Activations