© 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. 239185
    Prev
    Next
    INDEX
    Explanations

    Lists, locations, incidents

    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
     immerse
    0.38
     midrange
    0.38
    inct
    0.37
    শার
    0.37
    中期
    0.36
    諸
    0.36
     subl
    0.36
    瘟
    0.36
    하다
    0.35
    धुनिक
    0.35
    POSITIVE LOGITS
    ([])
    0.45
     (>
    0.40
    NonUser
    0.39
     gleichzeitig
    0.37
    ExternalTaskPojo
    0.37
     multidis
    0.37
     samos
    0.37
     مسجد
    0.36
     regulación
    0.36
    ведена
    0.36
    Activations Density 0.001%

    No Known Activations