© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44134
    Prev
    Next
    INDEX
    Explanations

    initials followed by periods

    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_22_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
     fenêtre
    0.41
    κό
    0.38
    Firefox
    0.37
    가
    0.37
    Produto
    0.37
    Azure
    0.37
    Cann
    0.36
     Justiça
    0.36
     Metaverse
    0.36
    에
    0.36
    POSITIVE LOGITS
     Uhr
    0.37
    imat
    0.36
    BuildAction
    0.34
     Galveston
    0.34
     comport
    0.34
    imak
    0.34
     clocks
    0.34
     বিশ্বকাপ
    0.34
    acher
    0.33
     sampled
    0.33
    Activations Density 0.001%

    No Known Activations