© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120635
    Prev
    Next
    INDEX
    Explanations

    -

    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_27_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
    攪
    0.41
    发布的
    0.40
    麿
    0.39
     carc
    0.38
    Три
    0.38
    奐
    0.38
    接觸
    0.37
    Nurse
    0.37
     publishers
    0.36
    اف
    0.36
    POSITIVE LOGITS
     shabby
    0.43
    bahnhof
    0.39
    tempCard
    0.38
    ຽ
    0.38
    vercel
    0.37
     worn
    0.37
     humbly
    0.37
     slums
    0.37
    kowitz
    0.37
     bato
    0.36
    Activations Density 0.010%

    No Known Activations