© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212744
    Prev
    Next
    INDEX
    Explanations

    Motive

    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_5_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
    ти
    1.63
    ี
    1.56
    -
    1.38
    س
    1.37
    та
    1.30
    uk
    1.26
    ill
    1.24
    с
    1.24
    மாக
    1.23
    ir
    1.15
    POSITIVE LOGITS
    t
    1.54
    ፫
    1.00
    z
    0.99
    אל
    0.96
     Бүген
    0.96
    jač
    0.96
    {
    0.95
    자
    0.95
    ភ្
    0.95
    zinho
    0.94
    Activations Density 0.000%

    No Known Activations