© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31308
    Prev
    Next
    INDEX
    Explanations

    he hears

    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
    گن
    0.26
    捨て
    0.26
     magar
    0.26
    芻
    0.26
     gmin
    0.25
    ठी
    0.25
    یی
    0.24
    暖
    0.24
    ennials
    0.24
    auti
    0.24
    POSITIVE LOGITS
    ורה
    0.27
    住在
    0.27
     informed
    0.26
     живу
    0.26
    댁
    0.26
     Vertex
    0.26
     ब्राह
    0.26
    цэ
    0.25
     layman
    0.25
     স্ট্যান্ডার্ড
    0.25
    Activations Density 0.002%

    No Known Activations