© 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. 115827
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    /
    0.46
    <0xEB>
    0.43
    _
    0.41
    declar
    0.40
    F
    0.39
    訢
    0.39
    project
    0.38
    으로
    0.38
    이
    0.38
     l
    0.38
    POSITIVE LOGITS
    蟶
    0.48
    प्रेशन
    0.43
     vurg
    0.38
    വദ
    0.36
    抟
    0.36
     TimeSpan
    0.35
     চট্টগ্রামে
    0.35
     productImage
    0.35
    classAttribute
    0.35
    كُمْ
    0.35
    Activations Density 0.000%

    No Known Activations