© 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. 43968
    Prev
    Next
    INDEX
    Explanations

    post- words

    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
    ᡧ
    0.64
     dünya
    0.64
    ྦ
    0.63
    タリア
    0.60
     northern
    0.59
     ľud
    0.59
     championnat
    0.58
    ムー
    0.58
    버
    0.58
     É
    0.57
    POSITIVE LOGITS
    :
    0.78
    ه
    0.77
    ut
    0.76
    2
    0.76
    im
    0.69
    un
    0.65
    o
    0.64
    1
    0.64
    iles
    0.62
    ’’
    0.60
    Activations Density 0.005%

    No Known Activations