© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175728
    Prev
    Next
    INDEX
    Explanations

    story and status updates

    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_20_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
     приорите
    0.22
    рее
    0.22
    kWh
    0.21
     Distillery
    0.21
     ～
    0.21
    туру
    0.21
    вни
    0.21
     जितने
    0.20
     GHz
    0.20
    Yvette
    0.20
    POSITIVE LOGITS
    jected
    0.21
    jama
    0.21
     laga
    0.18
    zew
    0.18
    irit
    0.18
    ânico
    0.18
    郑
    0.18
     multifunctional
    0.18
    ினான்
    0.18
     characters
    0.17
    Activations Density 0.000%

    No Known Activations