© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34794
    Prev
    Next
    INDEX
    Explanations

    book titles and marketing

    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_50_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
    </i>
    0.39
     American
    0.35
     Bally
    0.33
     مح
    0.33
     الش
    0.32
     éton
    0.32
     kawasan
    0.32
    职业
    0.32
     अमेरिकी
    0.32
     Community
    0.31
    POSITIVE LOGITS
    SimpleDateFormat
    0.34
    ๊
    0.32
    르
    0.31
    irthday
    0.30
    ఋ
    0.30
    Stop
    0.29
     ofstream
    0.29
    Disagree
    0.29
     localVarAccept
    0.29
    urnd
    0.29
    Activations Density 0.001%

    No Known Activations