© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31311
    Prev
    Next
    INDEX
    Explanations

    words starting with 't'

    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_31_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
     stick
    0.27
     اسم
    0.26
     sticking
    0.25
     Lerner
    0.25
     name
    0.24
    狀
    0.24
     Alger
    0.24
     wiped
    0.24
     nomencl
    0.23
     nomenclature
    0.23
    POSITIVE LOGITS
    軹
    0.30
    दुर्
    0.27
    िक्र
    0.26
    BMW
    0.26
    traffic
    0.26
    轵
    0.25
    血糖
    0.24
     генерал
    0.24
    Hobbies
    0.24
    涧
    0.24
    Activations Density 0.024%

    No Known Activations