© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28568
    Prev
    Next
    INDEX
    Explanations

    php code blocks

    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_40_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
     requests
    0.40
     sets
    0.39
    MNumber
    0.37
     essential
    0.36
     narr
    0.36
     probleem
    0.36
    馆
    0.35
     форум
    0.35
     justifies
    0.35
    胜
    0.34
    POSITIVE LOGITS
    /*
    0.47
    foreach
    0.46
    artificial
    0.42
    Pose
    0.39
     perdagangan
    0.39
    ╱
    0.38
     Crac
    0.37
    格
    0.37
    <em>
    0.37
     Ary
    0.37
    Activations Density 0.001%

    No Known Activations