© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154694
    Prev
    Next
    INDEX
    Explanations

    tech companies and funding

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     bueno
    0.43
    تقاوى
    0.42
    لیل
    0.40
    לב
    0.39
     Kitty
    0.39
    ῴ
    0.39
     Reyn
    0.38
     کوڈ
    0.37
    光源
    0.37
     पेनल
    0.37
    POSITIVE LOGITS
    檩
    0.45
    alled
    0.44
    原
    0.41
     оте
    0.40
    iada
    0.38
    ንዳ
    0.37
     Oman
    0.37
    ADEM
    0.37
    ggle
    0.37
     हरिद्वार
    0.37
    Activations Density 0.003%

    No Known Activations