© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58038
    Prev
    Next
    INDEX
    Explanations

    adjectives after "is"

    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_11_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
     equaling
    0.64
    榫
    0.64
     berücksichtigt
    0.63
     asymmetries
    0.62
     VLAN
    0.62
    एशन
    0.61
     stylesheets
    0.59
    εν
    0.59
    搜索引擎
    0.57
     Berechnung
    0.57
    POSITIVE LOGITS
    an
    0.73
    ک
    0.71
    ल
    0.70
     iki
    0.66
    ק
    0.65
    वानी
    0.65
    kar
    0.62
    ки
    0.60
     coast
    0.60
    ল
    0.60
    Activations Density 0.001%

    No Known Activations