© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50790
    Prev
    Next
    INDEX
    Explanations

    polio and vaccines

    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_30_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
     glTexCoord
    0.29
     счастли
    0.28
    ദ്ധ
    0.28
    瑞
    0.28
    号码
    0.27
    ഭാഗ
    0.27
    PartOf
    0.27
    cusson
    0.26
    blems
    0.26
    createComponent
    0.26
    POSITIVE LOGITS
     Yoshi
    0.30
    学習
    0.28
    jm
    0.27
    ₁,
    0.27
     unsh
    0.27
     пъ
    0.27
    fecha
    0.27
     commun
    0.26
     palate
    0.26
    Pool
    0.26
    Activations Density 0.000%

    No Known Activations