© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16240
    Prev
    Next
    INDEX
    Explanations

    **Explaining Neuron Activity**I'm tasked with explaining a neuron's behavior using patterns from four lists: `TOP_POSITIVE_LOGITS`, `TOP_ACTIVATING_TEXTS`, `MAX_ACTIVATING_TOKENS`, and `TOKENS_AFTER_MAX_ACTIVATING_TOKEN`. The explanation should be a concise phrase (3-20 words), specific, and avoid certain introductory phrases.Let's analyze the provided data:1. **`MAX_ACTIVATING_TOKENS`**: * might *

    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_15_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
    cken
    0.17
    chtigt
    0.16
    selt
    0.14
     dall
    0.14
    സാ
    0.14
     te
    0.13
    ிக
    0.13
    albeit
    0.13
    iglas
    0.13
    igten
    0.13
    POSITIVE LOGITS
     infringe
    0.17
     bahawa
    0.17
    ícul
    0.16
     ప్రకారం
    0.16
     появились
    0.15
    ຸນ
    0.15
     clearInterval
    0.15
    FuncName
    0.15
     ná
    0.15
     triángulo
    0.15
    Activations Density 0.122%

    No Known Activations