© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37447
    Prev
    Next
    INDEX
    Explanations

    Media Center

    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
    t
    1.18
    ت
    1.01
    ل
    0.99
    т
    0.89
    ون
    0.85
    AY
    0.85
    AD
    0.79
    л
    0.77
    с
    0.77
    API
    0.75
    POSITIVE LOGITS
     a
    0.88
     sencillo
    0.81
     phasing
    0.79
     y
    0.78
     οποίο
    0.77
     commas
    0.76
     методы
    0.76
     estuv
    0.75
     oleh
    0.75
     allemand
    0.75
    Activations Density 0.010%

    No Known Activations