© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130265
    Prev
    Next
    INDEX
    Explanations

    winning a

    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_6_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
    ad
    1.49
    ق
    1.20
    ש
    1.16
    w
    1.13
    ح
    1.02
    x
    0.97
    もの
    0.96
    ר
    0.96
    एस
    0.89
    3
    0.89
    POSITIVE LOGITS
    在
    1.36
     in
    1.19
    ও
    0.94
    في
    0.90
    től
    0.84
     berücksichtigt
    0.80
    枌
    0.80
    tól
    0.79
     في
    0.78
     కలిగి
    0.78
    Activations Density 0.001%

    No Known Activations