© 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. 143584
    Prev
    Next
    INDEX
    Explanations

    parametric

    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
     be
    2.00
    ला
    1.95
     as
    1.89
    is
    1.73
     the
    1.65
    ↵
    1.61
    at
    1.56
    as
    1.44
    на
    1.43
    ется
    1.41
    POSITIVE LOGITS
    ﺭ
    1.53
     لأ
    1.38
     tradiz
    1.32
     γεγον
    1.30
    ı
    1.27
     следова
    1.27
     слабы
    1.25
    י
    1.25
    ي
    1.20
    限于
    1.17
    Activations Density 0.000%

    No Known Activations