© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44087
    Prev
    Next
    INDEX
    Explanations

    wanna go

    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_13_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
    込む
    0.52
     Governments
    0.50
    کو
    0.47
    ের
    0.45
    वे
    0.45
    也
    0.45
    ंज
    0.44
    ใน
    0.44
    성을
    0.43
    柏
    0.43
    POSITIVE LOGITS
     absorb
    0.53
     o
    0.52
     absor
    0.49
     elastic
    0.48
     assail
    0.48
    se
    0.48
     crick
    0.47
     ga
    0.47
    able
    0.46
     ecl
    0.46
    Activations Density 0.000%

    No Known Activations