© 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. 166297
    Prev
    Next
    INDEX
    Explanations

    data comparison

    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
    sud
    0.41
    lnk
    0.40
    突然
    0.36
     தடை
    0.36
     ¶
    0.35
     अचानक
    0.34
    ONG
    0.34
    }]_{
    0.34
    शोर
    0.33
    数字化
    0.33
    POSITIVE LOGITS
     test
    0.43
     тест
    0.39
    ทด
    0.39
     known
    0.39
    Ꮠ
    0.38
     тести
    0.38
    Serializable
    0.38
    テスト
    0.37
    ueux
    0.37
     精
    0.36
    Activations Density 0.002%

    No Known Activations