© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251148
    Prev
    Next
    INDEX
    Explanations

    Tal

    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_56_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
     T
    1.90
    T
    1.70
     Т
    1.58
    Т
    1.36
     t
    1.31
     ט
    1.30
     ტ
    1.26
     الت
    1.23
    Ｔ
    1.20
     Τ
    1.18
    POSITIVE LOGITS
    Tal
    0.68
     Tal
    0.66
     tal
    0.59
    tal
    0.58
     TAL
    0.50
     тала
    0.50
     Talbot
    0.49
     hög
    0.44
     longer
    0.43
     tallied
    0.43
    Activations Density 0.005%

    No Known Activations