© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14183
    Prev
    Next
    INDEX
    Explanations

    doing chores and 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_34_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
    proto
    0.41
    ွေး
    0.39
     сорта
    0.39
     whats
    0.37
    Kab
    0.37
     adher
    0.36
     protagonist
    0.36
    선
    0.36
     ader
    0.35
    whats
    0.34
    POSITIVE LOGITS
     laundry
    0.53
     filing
    0.49
     chores
    0.45
     Laundry
    0.44
     taxes
    0.42
     做
    0.41
     Taxes
    0.40
     робити
    0.40
    Laundry
    0.39
     groceries
    0.38
    Activations Density 0.082%

    No Known Activations