© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61934
    Prev
    Next
    INDEX
    Explanations

    feminine past participle ending

    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
     on
    1.55
    as
    1.45
    ة
    1.44
    та
    1.38
    的
    1.38
     are
    1.32
    ي
    1.30
    ا
    1.27
    ت
    1.26
    その
    1.23
    POSITIVE LOGITS
    ال
    1.11
    1
    0.93
    ng
    0.92
    xin
    0.88
    dale
    0.88
     enlev
    0.86
     Quatre
    0.86
    st
    0.85
    oc
    0.85
     footh
    0.85
    Activations Density 0.000%

    No Known Activations