© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82019
    Prev
    Next
    INDEX
    Explanations

    Letter t

    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_53_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
    hati
    0.40
     indifer
    0.39
    fif
    0.38
    atim
    0.37
     Inert
    0.37
    <unused11>
    0.36
     KOH
    0.36
     Ignore
    0.35
    ষেধ
    0.35
     elsif
    0.35
    POSITIVE LOGITS
     т
    1.66
     t
    1.42
     ت
    1.14
     त
    1.13
     ত
    0.98
     ט
    0.89
    ｔ
    0.86
    т
    0.83
    ท
    0.83
    t
    0.73
    Activations Density 0.001%

    No Known Activations