© 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. 176344
    Prev
    Next
    INDEX
    Explanations

    say "t" words

    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
     ضبط
    0.40
    }\|_{
    0.40
     calorimeter
    0.39
    //*[@
    0.38
    𝙱
    0.38
     dv
    0.37
    alloway
    0.37
     Gron
    0.37
    ignet
    0.36
    ័យ
    0.36
    POSITIVE LOGITS
     TE
    1.32
     tea
    1.29
    Tea
    1.29
     テ
    1.25
    Te
    1.22
     Tea
    1.20
     테
    1.20
    Teen
    1.20
     TEA
    1.20
     Tee
    1.18
    Activations Density 0.001%

    No Known Activations