© 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. 36767
    Prev
    Next
    INDEX
    Explanations

    web3 wallet

    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
     are
    0.83
    ق
    0.78
    ↵↵
    0.74
    "。
    0.74
     a
    0.73
     was
    0.69
    ä
    0.68
    0.67
    ט
    0.67
     ***",
    0.66
    POSITIVE LOGITS
    on
    0.80
    ong
    0.76
    oric
    0.72
    igt
    0.70
    ishing
    0.68
    ъ
    0.68
    м
    0.67
    ını
    0.67
    iosis
    0.67
    ēng
    0.65
    Activations Density 0.035%

    No Known Activations