© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124501
    Prev
    Next
    INDEX
    Explanations

    no right or wrong

    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_37_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
     Right
    0.73
     right
    0.71
    右
    0.69
    Right
    0.65
     RIGHT
    0.65
     direita
    0.63
     righth
    0.63
     右
    0.61
     Left
    0.61
     left
    0.57
    POSITIVE LOGITS
     žmog
    0.41
    獅
    0.39
    bilt
    0.39
    ליך
    0.38
    encoding
    0.38
    cko
    0.38
     מספר
    0.37
    鐐
    0.36
    王朝
    0.36
     स्पष्ट
    0.35
    Activations Density 0.003%

    No Known Activations