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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62927
    Prev
    Next
    INDEX
    Explanations

    future intent

    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_41_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
     će
    0.43
     will
    0.43
     sẽ
    0.40
     देंगे
    0.40
     irá
    0.39
    憚
    0.39
    会
    0.38
    會
    0.38
    擇
    0.38
     akan
    0.38
    POSITIVE LOGITS
     shall
    1.18
     Shall
    1.03
    shall
    1.01
    Shall
    0.97
     skal
    0.88
     SHALL
    0.87
     sollen
    0.82
     ska
    0.80
     skall
    0.75
     fhall
    0.72
    Activations Density 0.044%

    No Known Activations