© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7587
    Prev
    Next
    INDEX
    Explanations

    colon cancer

    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_40_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
    ப்பே
    0.38
     daughter
    0.37
    ўнай
    0.36
     freezer
    0.35
    兢
    0.35
     daughters
    0.35
     LOGIN
    0.35
    部分
    0.35
     login
    0.35
    REG
    0.35
    POSITIVE LOGITS
    iali
    0.39
    خد
    0.39
    ৈ
    0.38
     ܀
    0.38
    êts
    0.37
    Hydro
    0.37
    reqParams
    0.37
     تقس
    0.37
     говори
    0.36
    Noise
    0.36
    Activations Density 0.023%

    No Known Activations