© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139017
    Prev
    Next
    INDEX
    Explanations

    plumage and wings

    np_acts-logits-general · gemini-2.5-flash-lite

    bird parts

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    present tense verbs ending in 'ing'.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    ifon
    0.48
    同時に
    0.40
     Flügel
    0.40
    s
    0.39
    ian
    0.39
    ino
    0.39
     Conditional
    0.39
    Д
    0.39
     D
    0.39
    ário
    0.39
    POSITIVE LOGITS
     egypt
    0.54
     země
    0.53
    를
    0.50
     famille
    0.48
     kunde
    0.47
    काम
    0.47
     කිරීම
    0.47
     agricultura
    0.47
     quelconque
    0.46
    
    0.46
    Activations Density 0.003%

    No Known Activations