© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4895
    Prev
    Next
    INDEX
    Explanations

    pronouns with verbs

    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
    Confident
    0.36
    棦
    0.35
    தர
    0.34
    Personally
    0.34
    榆
    0.33
    Ձ
    0.33
     एक्टिंग
    0.33
    앵
    0.33
     ውስ
    0.32
    jas
    0.32
    POSITIVE LOGITS
    getitem
    0.38
     ammunition
    0.36
     ticks
    0.34
    ிடம்
    0.32
     skulls
    0.31
    ivation
    0.31
    acoes
    0.31
    ivities
    0.31
    ုန်း
    0.31
     কা
    0.30
    Activations Density 0.057%

    No Known Activations