© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155176
    Prev
    Next
    INDEX
    Explanations

    tea

    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_60_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
     Tea
    3.06
     tea
    3.02
    Tea
    2.97
     TEA
    2.72
    茶
    2.67
    tea
    2.64
    TEA
    2.41
     чай
    2.34
     茶
    2.17
     चाय
    2.09
    POSITIVE LOGITS
    ITHUB
    0.37
    驄
    0.36
     Dura
    0.35
    ibers
    0.35
     Everett
    0.34
    assers
    0.34
    炇
    0.33
    旂
    0.33
     Pacífico
    0.32
     Catholicism
    0.32
    Activations Density 0.005%

    No Known Activations