© 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. 37524
    Prev
    Next
    INDEX
    Explanations

    0

    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
    GetInt
    0.39
    zit
    0.38
    チン
    0.37
    엿
    0.36
    انات
    0.36
    ᱧ
    0.36
    lockSeconds
    0.35
    ziła
    0.35
    зи
    0.35
    ይታ
    0.35
    POSITIVE LOGITS
    erne
    0.39
     SDF
    0.39
     Ah
    0.38
     ACF
    0.38
     FD
    0.38
     EOS
    0.38
     MDF
    0.37
    🥞
    0.37
     merge
    0.37
     আব্দ
    0.37
    Activations Density 0.004%

    No Known Activations