© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8377
    Prev
    Next
    INDEX
    Explanations

    employment and opportunity

    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_40_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
     하
    0.38
    stechn
    0.36
    bill
    0.35
     Bill
    0.35
     Mission
    0.35
     shows
    0.35
     Beacon
    0.35
    ź
    0.35
     Late
    0.34
    performance
    0.34
    POSITIVE LOGITS
    කා
    0.37
    ികൾ
    0.36
     Nak
    0.35
     evangel
    0.34
     overlook
    0.33
    mxCell
    0.33
    უქ
    0.32
     motorists
    0.32
    Nak
    0.32
     (!$
    0.31
    Activations Density 0.018%

    No Known Activations