© 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. 12051
    Prev
    Next
    INDEX
    Explanations

    atomic masses

    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
     अस्
    0.36
    ovost
    0.35
     exchanged
    0.35
     phosphat
    0.35
    ỵ
    0.35
     парт
    0.34
     Organic
    0.33
    LoginForm
    0.33
    Definitely
    0.33
    党
    0.33
    POSITIVE LOGITS
    ទុក
    0.41
     রিপোর্টে
    0.40
     crow
    0.39
     Fife
    0.39
     منت
    0.39
    BUCK
    0.39
    report
    0.37
     droid
    0.36
    Wrapped
    0.36
    Report
    0.35
    Activations Density 0.013%

    No Known Activations