© 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. 143527
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
    ó
    1.90
    ا
    1.84
    、
    1.84
     be
    1.77
    ت
    1.77
    س
    1.76
    ار
    1.63
    ম
    1.63
    ни
    1.62
    م
    1.55
    POSITIVE LOGITS
    9
    1.42
    کرد
    1.39
     sfondo
    1.35
     که
    1.31
     علی
    1.31
    ﺎ
    1.30
     حتی
    1.29
     فی
    1.28
     elucid
    1.27
    رک
    1.25
    Activations Density 0.001%

    No Known Activations