© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173978
    Prev
    Next
    INDEX
    Explanations

    astronaut names

    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
     Trying
    0.38
    compiled
    0.38
    Trying
    0.36
    Descriptions
    0.33
    smtp
    0.33
    Printed
    0.32
    이블
    0.32
    })$
    0.32
    nés
    0.32
    czyk
    0.32
    POSITIVE LOGITS
     center
    0.38
     öd
    0.38
     özelliği
    0.37
     yada
    0.37
    υ
    0.36
     sağlık
    0.36
     Heartland
    0.35
     Governors
    0.35
     Regione
    0.34
     Road
    0.34
    Activations Density 0.000%

    No Known Activations