© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204156
    Prev
    Next
    INDEX
    Explanations

    curl_setopt

    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_37_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
    📘
    0.39
    愊
    0.39
    <unused8>
    0.38
    PHP
    0.38
    phenoxymethyl
    0.38
     associate
    0.37
     notebook
    0.37
    Missense
    0.37
     সাধ
    0.36
    мино
    0.36
    POSITIVE LOGITS
    bev
    0.40
    ിലാ
    0.40
    yen
    0.38
    чні
    0.38
    측
    0.37
     Administration
    0.36
    urgent
    0.36
    yal
    0.36
     Sh
    0.35
     Anyways
    0.35
    Activations Density 0.000%

    No Known Activations