© 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. 44375
    Prev
    Next
    INDEX
    Explanations

    method resolution order

    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
    1
    1.09
    on
    1.01
    5
    0.93
    6
    0.91
    och
    0.90
    ت
    0.89
    3
    0.89
    4
    0.89
    oz
    0.88
    2
    0.88
    POSITIVE LOGITS
    и
    0.74
    й
    0.73
     descenso
    0.71
    у
    0.71
    р
    0.70
     magically
    0.70
     persegu
    0.70
    우
    0.70
     svjets
    0.69
     ugljik
    0.69
    Activations Density 0.002%

    No Known Activations