© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12204
    Prev
    Next
    INDEX
    Explanations

    immune modulation or suppression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     сертифика
    0.51
     certifications
    0.49
     certification
    0.49
     examinations
    0.48
     கல்வி
    0.47
    🈯
    0.46
     শিক্ষার
    0.46
    ផុត
    0.46
     certificate
    0.45
     શિક્ષણ
    0.44
    POSITIVE LOGITS
    ag
    0.51
    Region
    0.50
    REGION
    0.48
    vm
    0.46
    et
    0.46
    IP
    0.45
    ack
    0.44
    IM
    0.43
    v
    0.42
    G
    0.42
    Activations Density 0.016%

    No Known Activations