© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77639
    Prev
    Next
    INDEX
    Explanations

    useState hook

    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_31_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
     nationalism
    0.38
    дни
    0.38
    <0xD1>
    0.35
    здат
    0.35
    வதில்
    0.34
    擔任
    0.34
     malu
    0.34
    ዝና
    0.34
    फिकेशन
    0.33
    ancji
    0.33
    POSITIVE LOGITS
     Nunca
    0.40
     Lipp
    0.40
     Pois
    0.39
     Abuse
    0.39
     Weapons
    0.39
    事
    0.38
    Nunca
    0.37
     Weapon
    0.36
    🚃
    0.36
     armas
    0.35
    Activations Density 0.001%

    No Known Activations