© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53721
    Prev
    Next
    INDEX
    Explanations

    list or code continuations

    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_31_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
    אן
    0.35
     %#
    0.35
    िरपेक्ष
    0.34
     emphasised
    0.33
     %)
    0.33
     ageing
    0.32
     alış
    0.32
     aging
    0.31
     regularmente
    0.31
     रिमाइंडर
    0.31
    POSITIVE LOGITS
    oc
    0.34
    getSelectedItem
    0.33
    Taken
    0.33
     ME
    0.33
     May
    0.32
    特
    0.32
    ME
    0.31
    Generator
    0.31
    шена
    0.30
     हज़ार
    0.30
    Activations Density 0.076%

    No Known Activations