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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165224
    Prev
    Next
    INDEX
    Explanations

    Axis-Aligned Bounding Box (AABB)

    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_13_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
     c
    0.53
    زر
    0.52
    c
    0.50
     Startup
    0.47
    Comb
    0.46
     B
    0.46
    ేశ
    0.45
    Racing
    0.45
    م
    0.45
    atically
    0.45
    POSITIVE LOGITS
    сию
    0.61
     eighteenth
    0.58
     individus
    0.57
     PARK
    0.57
     errichtet
    0.57
     park
    0.56
     quinquina
    0.55
     eighteen
    0.55
     ఉంట
    0.55
     одновременно
    0.55
    Activations Density 0.004%

    No Known Activations