© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52957
    Prev
    Next
    INDEX
    Explanations

    people with professions or roles

    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_30_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
    lifts
    0.37
    Click
    0.36
     Decode
    0.35
     Explore
    0.35
     Click
    0.34
    oom
    0.34
    ބ
    0.34
     about
    0.33
     Dig
    0.33
    Gram
    0.33
    POSITIVE LOGITS
    σωπ
    0.42
    ৤
    0.40
     comprado
    0.39
    ܠܐ
    0.39
    áus
    0.37
    Raquete
    0.37
     Biele
    0.37
     Daughters
    0.36
     reglamento
    0.36
    ולנד
    0.36
    Activations Density 0.011%

    No Known Activations