© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61456
    Prev
    Next
    INDEX
    Explanations

    Japanese language

    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_59_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
    の
    0.96
    의
    0.89
    的
    0.80
     の
    0.70
     ones
    0.68
     followed
    0.59
    ের
    0.58
    च्या
    0.58
    ची
    0.57
    nya
    0.56
    POSITIVE LOGITS
    とその
    0.50
     kuten
    0.47
    余
    0.42
    과
    0.41
    にあ
    0.40
    เช่น
    0.40
    DataMat
    0.38
     Seperti
    0.38
     כמו
    0.37
    に使用
    0.37
    Activations Density 0.000%

    No Known Activations