© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 208682
    Prev
    Next
    INDEX
    Explanations

    filename processing

    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_20_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
    ட்சிய
    0.44
    ಂತಹ
    0.43
    菽
    0.42
    攽
    0.42
     outfielder
    0.40
     Eugenio
    0.40
    欵
    0.40
     Anakin
    0.40
    ITICAL
    0.39
    тник
    0.39
    POSITIVE LOGITS
    </b>
    0.42
     rows
    0.37
    Communities
    0.37
    Rows
    0.37
    username
    0.36
    enga
    0.36
    вело
    0.36
    Coul
    0.36
    cube
    0.36
    a
    0.36
    Activations Density 0.001%

    No Known Activations