© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260467
    Prev
    Next
    INDEX
    Explanations

    from around

    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
    िडी
    0.32
     ER
    0.31
     GO
    0.31
    radioButton
    0.31
     isLoading
    0.30
    aue
    0.30
     lineNumber
    0.30
    翔
    0.30
     occlusion
    0.30
     মুদ্রা
    0.30
    POSITIVE LOGITS
    плом
    0.39
    ajte
    0.35
    ös
    0.34
     görün
    0.32
     intéressant
    0.32
     świata
    0.32
     dépour
    0.32
    arsanız
    0.32
    ówki
    0.32
    ៍
    0.32
    Activations Density 0.002%

    No Known Activations