© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89054
    Prev
    Next
    INDEX
    Explanations

    greatest good for the greatest number

    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_3_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
    ا
    1.02
    ா
    0.84
    א
    0.79
    0.74
    מ
    0.74
    Chaos
    0.71
    Charset
    0.70
    ק
    0.66
    I
    0.66
    स
    0.66
    POSITIVE LOGITS
     greater
    0.84
    ने
    0.70
    ות
    0.68
     Greatest
    0.68
     greatest
    0.66
     Greater
    0.64
    ána
    0.63
    ется
    0.62
    áte
    0.62
     one
    0.61
    Activations Density 0.004%

    No Known Activations