© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122401
    Prev
    Next
    INDEX
    Explanations

    neovascularization, bronchovascular, lymphovascular invasion

    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_3_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
    a
    0.86
    า
    0.77
    *
    0.70
    e
    0.69
     Tshirt
    0.66
     Yoda
    0.66
    <0x85>
    0.63
    发出
    0.61
    o
    0.61
    吭
    0.61
    POSITIVE LOGITS
    ин
    0.80
    ang
    0.78
    ח
    0.70
    িল
    0.65
    ）,
    0.64
    াল
    0.64
    inte
    0.64
    يل
    0.62
    كان
    0.62
    كو
    0.61
    Activations Density 0.000%

    No Known Activations