© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59138
    Prev
    Next
    INDEX
    Explanations

    session management or idle machines

    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_11_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
    שת
    0.48
    ্সে
    0.47
    Issledovatel
    0.46
    c
    0.46
    WH
    0.45
    THRESH
    0.44
    Siempre
    0.43
    cknowled
    0.43
    اني
    0.42
     أيضاً
    0.41
    POSITIVE LOGITS
     griseo
    0.58
     soldiers
    0.52
     ligands
    0.51
    𝗳
    0.50
     adsorb
    0.49
    ສາມາດ
    0.49
    モス
    0.49
     elves
    0.48
    ສ
    0.47
     progenitors
    0.47
    Activations Density 0.000%

    No Known Activations