© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144329
    Prev
    Next
    INDEX
    Explanations

    indicated, indication

    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_0_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
    1
    1.38
    )
    1.38
    ana
    1.26
    ।’
    1.20
     for
    1.18
    не
    1.17
    7
    1.13
    的产品
    1.11
    itze
    1.10
    ên
    1.06
    POSITIVE LOGITS
    م
    2.31
    ب
    2.30
    ल
    1.68
    ו
    1.66
    ని
    1.59
    在
    1.59
    ق
    1.53
    ل
    1.52
    ون
    1.51
    म
    1.51
    Activations Density 0.000%

    No Known Activations