© 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. 166255
    Prev
    Next
    INDEX
    Explanations

    configuration and dependencies

    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
     ceramics
    0.40
     빙
    0.39
    graduate
    0.38
     얼
    0.36
     ധാ
    0.35
     acoustics
    0.34
     gradu
    0.34
    ਭ
    0.34
    ريم
    0.34
    oult
    0.34
    POSITIVE LOGITS
    Incre
    0.38
     анали
    0.37
    Ẩ
    0.37
    Tight
    0.37
     plus
    0.36
     decreases
    0.36
     ensues
    0.36
     restricts
    0.35
    Plus
    0.35
    Extract
    0.35
    Activations Density 0.001%

    No Known Activations