© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89431
    Prev
    Next
    INDEX
    Explanations

    words ending in ster

    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
    ۳
    0.43
    ！)
    0.43
     Vee
    0.42
     superconduct
    0.41
    創造
    0.41
    ᱢ
    0.41
     крупных
    0.41
    㡀
    0.40
    ！）
    0.40
    ਆਂ
    0.39
    POSITIVE LOGITS
    er
    0.50
    acks
    0.45
     aéri
    0.45
     gesamte
    0.45
    τή
    0.44
    larına
    0.43
     частина
    0.43
    ak
    0.43
     einzige
    0.41
     이후
    0.40
    Activations Density 0.000%

    No Known Activations