© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64100
    Prev
    Next
    INDEX
    Explanations

    physical labor or manual tasks

    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
     Demp
    0.37
    htp
    0.37
    ApiException
    0.36
    ್ಣ
    0.36
     Nang
    0.35
     Superhero
    0.34
    trop
    0.34
     ރ
    0.34
     Nagata
    0.34
     হোমিওপ্যাথির
    0.33
    POSITIVE LOGITS
     manual
    1.63
     Manual
    1.45
    manual
    1.45
     labor
    1.43
    Manual
    1.42
     labour
    1.30
     MANUAL
    1.30
    劳动
    1.23
    Labor
    1.21
     manually
    1.20
    Activations Density 0.069%

    No Known Activations