© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87360
    Prev
    Next
    INDEX
    Explanations

    you want

    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_23_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
    鿆
    0.47
     diminta
    0.45
    custList
    0.40
    楖
    0.40
     telah
    0.40
    㖵
    0.39
    栱
    0.39
    ⑸
    0.39
    бие
    0.39
    摸
    0.39
    POSITIVE LOGITS
    Whilst
    0.35
     Hong
    0.34
     Toolbox
    0.34
     따른
    0.34
     Nightingale
    0.34
    zon
    0.34
     Rev
    0.33
    geo
    0.33
     Haft
    0.33
     Pasand
    0.33
    Activations Density 0.002%

    No Known Activations