© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105752
    Prev
    Next
    INDEX
    Explanations

    elected officials Representatives

    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_1_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
    "
    1.34
    et
    1.17
    {
    1.16
    r
    1.03
    ↵
    1.02
    ви
    1.02
    esthetic
    0.93
    ad
    0.91
    ot
    0.91
    ר
    0.88
    POSITIVE LOGITS
    ك
    1.23
    یر
    1.22
    ang
    1.17
    ้าย
    1.17
    ONG
    1.10
    ە
    1.10
    しの
    1.09
    خ
    1.09
    מ
    1.09
    เป็น
    1.09
    Activations Density 0.000%

    No Known Activations