© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222812
    Prev
    Next
    INDEX
    Explanations

    sample

    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_10_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
    ną
    0.38
    л
    0.38
    น
    0.37
     t
    0.35
    anlı
    0.35
     اسرائی
    0.34
     т
    0.34
    ल
    0.33
    ル
    0.33
     NVIDIA
    0.32
    POSITIVE LOGITS
    6
    0.44
    3
    0.39
    5
    0.38
    1
    0.37
    2
    0.36
    4
    0.33
    8
    0.32
    acht
    0.32
     सैंपल
    0.31
     sample
    0.30
    Activations Density 0.007%

    No Known Activations