© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43605
    Prev
    Next
    INDEX
    Explanations

    bars and restaurants

    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_3_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
    ons
    0.65
    ↵↵
    0.64
    chée
    0.63
    "
    0.63
    هم
    0.61
    ,
    0.61
    و
    0.61
    benhav
    0.60
    )
    0.59
    bted
    0.59
    POSITIVE LOGITS
     တ
    0.81
    t
    0.66
     proviso
    0.65
     sumptuous
    0.64
     하나님의
    0.64
     cinco
    0.62
    れる
    0.62
     cinci
    0.61
     பால்
    0.59
    行って
    0.58
    Activations Density 0.003%

    No Known Activations