© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179450
    Prev
    Next
    INDEX
    Explanations

    high FMethod used: 3

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Teles
    0.43
    անում
    0.40
     gris
    0.40
    atiche
    0.39
    獐
    0.39
     Grimm
    0.38
     Tell
    0.38
     Yangzhou
    0.38
     Jacqueline
    0.38
     Trib
    0.37
    POSITIVE LOGITS
     f
    0.78
     F
    0.69
     ف
    0.63
    High
    0.63
     J
    0.62
     ফ
    0.56
     High
    0.55
     high
    0.53
    high
    0.52
    F
    0.52
    Activations Density 0.000%

    No Known Activations