© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260473
    Prev
    Next
    INDEX
    Explanations

    representatives from various groups

    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_22_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
     جوړونک
    0.50
    饼
    0.46
     coding
    0.44
     제품
    0.43
     प्रिंट
    0.42
     产品
    0.41
     coded
    0.41
     పరీక్ష
    0.41
     دوستان
    0.40
     municipality
    0.40
    POSITIVE LOGITS
    +#
    0.42
    ,+
    0.42
    organisation
    0.40
    le
    0.39
    PIPE
    0.39
     оказыва
    0.38
    activity
    0.38
    ле
    0.37
    менение
    0.37
    effects
    0.37
    Activations Density 0.002%

    No Known Activations