© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216843
    Prev
    Next
    INDEX
    Explanations

    medical roles

    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_47_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
     Morrow
    0.47
    Mor
    0.44
    ANA
    0.43
    aporte
    0.42
    /',
    0.42
    mor
    0.41
     Morr
    0.41
     médicas
    0.41
    तर
    0.40
    ᴥ
    0.40
    POSITIVE LOGITS
    ckers
    0.40
     alfabet
    0.38
    წ
    0.37
     bụi
    0.36
     স্ট
    0.36
    ynchus
    0.35
     Radar
    0.34
    existsSync
    0.34
    ඳ
    0.34
    печат
    0.34
    Activations Density 0.000%

    No Known Activations