© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13962
    Prev
    Next
    INDEX
    Explanations

    preposition or pre- words

    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_40_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
     facilities
    0.40
     kinetic
    0.38
     lantern
    0.38
     FACILITIES
    0.38
    ِر
    0.37
     Facilities
    0.37
     sis
    0.36
     Lantern
    0.35
     multiplicative
    0.35
    lantern
    0.35
    POSITIVE LOGITS
     preposition
    0.80
    Pre
    0.72
    pre
    0.70
     pre
    0.69
     пре
    0.68
     Pre
    0.67
    预
    0.63
    prep
    0.61
    Пре
    0.58
    預
    0.57
    Activations Density 0.204%

    No Known Activations