© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49967
    Prev
    Next
    INDEX
    Explanations

    * **MAX_ACTIVATING_TOKENS**: _ (Repeated, seems like it's marking a boundary or absence)* **TOKENS_AFTER_MAX_ACTIVATING_TOKEN**: `ACCESS`, `lambda`, `class`, `local`, `sign`, `read`, `bloc`, `facts`, `package`, `release`.Here's an explanation for the neuron's behavior:programming keywords following boundaries

    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_10_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
    ע
    0.26
    em
    0.26
    al
    0.26
    ع
    0.25
    er
    0.25
    ergy
    0.25
    ز
    0.24
    l
    0.24
    며
    0.24
    is
    0.24
    POSITIVE LOGITS
     രാഷ്ട്രീയ
    0.28
     políticos
    0.27
    CollectedField
    0.27
    vanje
    0.26
     resistant
    0.25
     downregulated
    0.25
     questione
    0.24
    ası
    0.24
     drank
    0.24
     screwed
    0.24
    Activations Density 0.008%

    No Known Activations