© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226035
    Prev
    Next
    INDEX
    Explanations

    pursue another opportunity

    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_10_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
    ला
    0.46
    uose
    0.44
     creato
    0.43
     মধ্যেও
    0.43
     proteção
    0.42
     numerosos
    0.42
     شعر
    0.40
    ো
    0.40
    ła
    0.40
     perguntas
    0.40
    POSITIVE LOGITS
    findById
    0.45
    2
    0.43
    P
    0.43
     amikor
    0.41
    一方
    0.40
    Y
    0.39
    ్‌
    0.39
    ab
    0.38
     vegg
    0.38
    办理
    0.38
    Activations Density 0.019%

    No Known Activations