© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80490
    Prev
    Next
    INDEX
    Explanations

    lone wolf

    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_0_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
    ت
    1.95
    س
    1.69
    4
    1.65
    ud
    1.59
    ong
    1.52
    та
    1.49
    1
    1.41
    ا
    1.39
    ö
    1.34
    ק
    1.34
    POSITIVE LOGITS
     i
    1.13
    ન
    1.09
    ин
    1.06
     y
    1.03
    ший
    1.03
     Wills
    1.03
     AppMethodBeat
    1.03
     být
    1.02
     který
    1.01
     ursprüng
    1.01
    Activations Density 0.001%

    No Known Activations