© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142668
    Prev
    Next
    INDEX
    Explanations

    whenever possible

    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
     It
    1.84
     in
    1.68
     it
    1.52
     If
    1.38
    m
    1.33
     In
    1.29
     Int
    1.09
    ssä
    1.09
     IFN
    1.07
    ren
    1.04
    POSITIVE LOGITS
    -
    2.19
    ী
    1.91
    ა
    1.91
    т
    1.70
    ה
    1.70
    ہ
    1.59
    ą
    1.59
    ین
    1.54
    ки
    1.52
    н
    1.52
    Activations Density 0.001%

    No Known Activations