© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10122
    Prev
    Next
    INDEX
    Explanations

    driving force, encouragement, motive

    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_13_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
    。
    0.12
    NIC
    0.11
    кле
    0.11
     sele
    0.11
    шу
    0.10
    рко
    0.10
    persky
    0.10
    ***********
    0.10
    کرو
    0.10
    ду
    0.10
    POSITIVE LOGITS
     coercion
    0.12
    ্লীল
    0.11
     genocide
    0.11
     још
    0.11
     নিয়ে
    0.11
     Bolo
    0.11
    追加
    0.11
     prostitution
    0.11
     provoking
    0.11
     hadi
    0.11
    Activations Density 0.096%

    No Known Activations