© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86067
    Prev
    Next
    INDEX
    Explanations

    agitation, aggression, seizures, depression

    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_23_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
    Browser
    0.14
    volving
    0.13
    Ice
    0.13
    漫画
    0.13
    x
    0.13
     divisão
    0.13
    注意事项
    0.13
    Status
    0.13
    *****
    0.13
     afectar
    0.13
    POSITIVE LOGITS
     Мето
    0.15
    сів
    0.14
     來
    0.14
    പ്പു
    0.14
     esi
    0.14
     setLayout
    0.14
     イン
    0.14
    Comté
    0.14
     配
    0.14
     компо
    0.13
    Activations Density 0.006%

    No Known Activations