© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15374
    Prev
    Next
    INDEX
    Explanations

    libs

    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_15_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
    льною
    0.17
    gin
    0.16
    {
    0.16
     immunosupp
    0.16
     preoccupation
    0.15
    <0x91>
    0.15
    ському
    0.15
    гід
    0.15
    Hi
    0.15
     premises
    0.15
    POSITIVE LOGITS
    x
    0.22
     Zor
    0.18
     climbers
    0.17
     x
    0.17
    thru
    0.17
     المنت
    0.17
    вета
    0.17
     almost
    0.17
     departe
    0.17
     כמה
    0.17
    Activations Density 0.004%

    No Known Activations