© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206446
    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_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
     {})
    0.49
    On
    0.43
     "/")
    0.40
     (:
    0.38
     '),
    0.38
    TimeDict
    0.37
     '.')
    0.37
    দ্ব
    0.37
    Contracts
    0.37
     ?)
    0.37
    POSITIVE LOGITS
     tha
    0.58
     Thé
    0.57
    ithe
    0.57
     thé
    0.56
     thei
    0.56
     thee
    0.53
     Tha
    0.52
     Thee
    0.52
     ث
    0.52
     ther
    0.51
    Activations Density 0.002%

    No Known Activations