© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196222
    Prev
    Next
    INDEX
    Explanations

    difficult at first

    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_26_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
     somebody
    0.43
     Creek
    0.42
     AGAIN
    0.42
     [{'
    0.41
     another
    0.41
     someone
    0.40
     cheap
    0.40
    search
    0.39
    追
    0.39
     মেন
    0.38
    POSITIVE LOGITS
    isVisible
    0.42
    دیا
    0.41
    ціа
    0.40
    ޚ
    0.39
    िखित
    0.38
    愆
    0.38
     وص
    0.38
    िल्
    0.37
     अकॉर्डिंग
    0.37
     Tatha
    0.37
    Activations Density 0.003%

    No Known Activations