© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198613
    Prev
    Next
    INDEX
    Explanations

    Japan entities

    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_12_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
    Opportunities
    0.43
    軖
    0.43
    Use
    0.42
    㡀
    0.42
    Ϩ
    0.41
    ینه
    0.41
    Protection
    0.41
    ເພື່ອ
    0.41
     වඩා
    0.41
    CompoundButton
    0.41
    POSITIVE LOGITS
     engulfed
    0.47
     úč
    0.45
     confounding
    0.44
     informants
    0.43
     locked
    0.43
    s
    0.42
     enslaved
    0.42
     journalism
    0.40
     literate
    0.39
     brave
    0.39
    Activations Density 0.000%

    No Known Activations