© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80513
    Prev
    Next
    INDEX
    Explanations

    pros, advantages, benefits

    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_31_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
     perplexing
    0.37
     یار
    0.36
     reconciling
    0.35
     puzzling
    0.35
    臥
    0.35
     dig
    0.34
     Galilee
    0.34
    람
    0.34
    Solving
    0.34
     Britannica
    0.34
    POSITIVE LOGITS
     shroud
    0.39
    ুলি
    0.39
     của
    0.38
     따르면
    0.37
    Ꮀ
    0.36
    <0x0F>
    0.35
     ریاست
    0.35
     प्रमोशन
    0.35
     propositions
    0.35
    耑
    0.35
    Activations Density 0.005%

    No Known Activations