© 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. 42296
    Prev
    Next
    INDEX
    Explanations

    butter cream cake

    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
    들이
    0.75
    یت
    0.59
    ید
    0.58
    nd
    0.55
     ลอง
    0.54
     योग्य
    0.54
    2
    0.54
    ع
    0.54
    یر
    0.53
     it
    0.53
    POSITIVE LOGITS
    т
    0.75
    IS
    0.68
    ت
    0.66
    AM
    0.66
    AN
    0.64
    AL
    0.64
    ｨ
    0.64
    з
    0.63
    ON
    0.62
    dP
    0.61
    Activations Density 0.000%

    No Known Activations