© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133428
    Prev
    Next
    INDEX
    Explanations

    stance

    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_1_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
     protrusions
    1.04
     isotopes
    1.02
     to
    1.01
     exams
    0.99
     decisions
    0.97
     routines
    0.96
    ਕ
    0.95
     є
    0.94
     explorations
    0.94
     abstractions
    0.93
    POSITIVE LOGITS
    I
    1.55
    (
    1.30
    {
    1.16
    (.*
    1.13
    лив
    1.11
    л
    1.10
    <0x80>
    1.09
    IL
    1.04
    的公司
    1.04
    ري
    1.03
    Activations Density 0.000%

    No Known Activations