© 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. 196148
    Prev
    Next
    INDEX
    Explanations

    congress and related government terms

    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
     गरज
    0.40
    neu
    0.37
    ૧
    0.36
     Told
    0.35
    อยู่ที่
    0.35
     इंटरव्यू
    0.34
     महाराष्ट
    0.34
    カフェ
    0.34
    oval
    0.34
    arian
    0.33
    POSITIVE LOGITS
     taxes
    0.42
     taxing
    0.39
     ও
    0.37
    ᱯ
    0.36
     pigments
    0.36
    taxes
    0.36
     impuesto
    0.35
     produced
    0.35
     taxa
    0.35
     improvements
    0.34
    Activations Density 0.000%

    No Known Activations