© 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. 129911
    Prev
    Next
    INDEX
    Explanations

    scene setting context

    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
    ㄼ
    0.41
    ㅀ
    0.39
     hason
    0.38
     leop
    0.37
     muffled
    0.37
    ریٹر
    0.36
     hs
    0.36
     accepté
    0.36
    盗
    0.36
    CEPTION
    0.35
    POSITIVE LOGITS
     amends
    0.45
     تحد
    0.39
    Gent
    0.37
     reiniciar
    0.37
     FormControl
    0.37
    granular
    0.36
     Tables
    0.36
    iska
    0.35
     gentle
    0.35
     Thousands
    0.35
    Activations Density 0.001%

    No Known Activations