© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129541
    Prev
    Next
    INDEX
    Explanations

    plus (cost, fees, expenses)

    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_25_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
     ""){
    0.40
    ipes
    0.39
    則是
    0.38
     λα
    0.37
    堯
    0.37
    join
    0.37
    Ã
    0.37
     delas
    0.37
    ais
    0.36
    ids
    0.35
    POSITIVE LOGITS
    लेकिन
    0.34
    ęcie
    0.33
    䏍
    0.33
     coûte
    0.33
    iembre
    0.32
     कैप्शन
    0.32
     sobriety
    0.31
    جمة
    0.31
    प्टन
    0.31
    㫻
    0.31
    Activations Density 0.002%

    No Known Activations