© 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. 125672
    Prev
    Next
    INDEX
    Explanations

    density related calculations and estimations

    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
    昧
    0.39
    ход
    0.38
    匆
    0.38
     chemist
    0.37
    buz
    0.36
     ge
    0.36
     supremac
    0.36
     buses
    0.36
    онов
    0.36
     б
    0.35
    POSITIVE LOGITS
    getAbsolutePath
    0.41
     चर्
    0.40
    構
    0.39
    一半
    0.38
    नाथन
    0.38
    ต่ำ
    0.37
     FIV
    0.37
    alisation
    0.36
     পায়নি
    0.36
    ートン
    0.35
    Activations Density 0.001%

    No Known Activations