© 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. 51101
    Prev
    Next
    INDEX
    Explanations

    influential historical figures

    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
     Newcastle
    0.38
     Upcoming
    0.37
    恍
    0.36
     attacked
    0.34
     हां
    0.33
     spawned
    0.33
    ége
    0.32
     hailed
    0.32
     coined
    0.32
     funded
    0.32
    POSITIVE LOGITS
    饋
    0.39
    contribution
    0.39
    brackets
    0.38
    paypal
    0.37
    Tenant
    0.37
    氣
    0.37
     பஞ்ச
    0.37
    麹
    0.36
     сразу
    0.36
     પ્રથમ
    0.36
    Activations Density 0.014%

    No Known Activations