© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3428
    Prev
    Next
    INDEX
    Explanations

    say "w" 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_44_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
    ('/').
    0.42
    }`))
    0.40
     धर
    0.38
     soit
    0.38
     Oles
    0.38
     Werner
    0.38
     InputMaybe
    0.37
     Nant
    0.37
     Biscuit
    0.36
     struck
    0.36
    POSITIVE LOGITS
    නී
    0.36
    κών
    0.36
    启动
    0.35
    ÑA
    0.34
    <>();
    0.34
    ("");
    0.33
    ­
    0.33
     tou
    0.33
    match
    0.32
    Gar
    0.32
    Activations Density 0.364%

    No Known Activations