© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109924
    Prev
    Next
    INDEX
    Explanations

    Dar and two

    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_2_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
    の見
    0.94
    繍
    0.94
     giardino
    0.93
    的需求
    0.92
     costante
    0.90
     livre
    0.89
     permesso
    0.89
     complejo
    0.88
     nouvelle
    0.87
     crescente
    0.87
    POSITIVE LOGITS
    :
    1.45
    3
    1.31
    0
    1.25
    4
    1.17
    es
    1.11
     as
    1.09
    ant
    1.07
    ur
    1.05
    "
    1.05
    5
    1.01
    Activations Density 0.000%

    No Known Activations