© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37617
    Prev
    Next
    INDEX
    Explanations

    say !

    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_57_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
     son
    0.46
     ha
    0.44
     (++
    0.41
     ehe
    0.40
     completely
    0.37
     Lu
    0.37
     tm
    0.37
     lu
    0.37
    Lu
    0.37
     guess
    0.36
    POSITIVE LOGITS
    বাজ
    0.42
    ынша
    0.39
     చేయ
    0.38
    бран
    0.36
     evicted
    0.36
    箐
    0.35
     disbursed
    0.35
     etiqu
    0.34
    ጉ
    0.34
     concurring
    0.34
    Activations Density 0.003%

    No Known Activations