© 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. 145156
    Prev
    Next
    INDEX
    Explanations

    dynamic keyword insertion

    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
     are
    2.03
    us
    1.82
    as
    1.77
    ia
    1.70
     on
    1.65
    ت
    1.55
     to
    1.53
    ू
    1.49
     or
    1.46
    я
    1.43
    POSITIVE LOGITS
    もら
    1.52
    야
    1.38
    도
    1.36
    も
    1.35
     인한
    1.33
     взрос
    1.24
     correto
    1.22
    스를
    1.21
    kę
    1.16
    Еще
    1.15
    Activations Density 0.001%

    No Known Activations