© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198896
    Prev
    Next
    INDEX
    Explanations

    "National" and "Water" policies

    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_27_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
     وكانت
    0.21
    ेष
    0.20
    thisTrack
    0.19
    ካከል
    0.19
    ("../../
    0.19
    鹘
    0.19
    <unused1160>
    0.18
    狒
    0.18
     পরিবেশ
    0.18
    繭
    0.18
    POSITIVE LOGITS
    IZATION
    0.20
    Cool
    0.20
    What
    0.19
     inappropri
    0.19
     #
    0.19
    滋
    0.19
     عالی
    0.18
    cium
    0.18
    czaj
    0.18
     chắn
    0.18
    Activations Density 0.000%

    No Known Activations