© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90635
    Prev
    Next
    INDEX
    Explanations

    sum of squares

    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_3_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
    orene
    0.64
    ركه
    0.64
     Ке
    0.62
     некоторые
    0.60
     Gosudarstvennyj
    0.59
    뷊
    0.59
    тальян
    0.59
     Государ
    0.58
    AGEN
    0.58
     Одна
    0.57
    POSITIVE LOGITS
     be
    0.88
    。
    0.87
    ش
    0.87
    S
    0.83
    of
    0.80
    ல்
    0.78
     was
    0.77
     s
    0.75
     not
    0.75
    ส
    0.75
    Activations Density 0.001%

    No Known Activations