© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202376
    Prev
    Next
    INDEX
    Explanations

    Japan

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    turns
    0.42
    custList
    0.41
    𝐞
    0.41
    use
    0.40
     guys
    0.39
    USE
    0.38
    fuel
    0.38
    listOf
    0.38
    मतौर
    0.38
    REMOVE
    0.37
    POSITIVE LOGITS
     kose
    0.41
     Jpn
    0.40
    ญี่ปุ่น
    0.40
     Japan
    0.40
     Jepang
    0.40
    馭
    0.40
     japonais
    0.39
     Gén
    0.39
     Smyrna
    0.39
     fluct
    0.39
    Activations Density 0.000%

    No Known Activations