© 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. 31322
    Prev
    Next
    INDEX
    Explanations

    html tag generation

    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
    regon
    0.39
    果
    0.37
    LockButton
    0.37
     রানের
    0.37
    dSample
    0.36
    Payments
    0.35
    िर
    0.35
    ርዓ
    0.33
    TaskManager
    0.33
    क्षेत्र
    0.33
    POSITIVE LOGITS
    ሃ
    0.43
     Garg
    0.40
     Br
    0.38
     Spitz
    0.38
     Bo
    0.37
     الاحت
    0.37
    ravenous
    0.37
    Oz
    0.36
     Hym
    0.36
     Sequencing
    0.36
    Activations Density 0.004%

    No Known Activations