© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237755
    Prev
    Next
    INDEX
    Explanations

    city as a field or data element

    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_25_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
     スーツ
    0.46
    ᕗ
    0.44
    堝
    0.44
     відео
    0.43
    動画
    0.42
    ኞ
    0.41
    𝚟
    0.40
    賈
    0.39
     numero
    0.38
     വീഡിയോ
    0.38
    POSITIVE LOGITS
     understanding
    0.39
    endenza
    0.38
     Monarch
    0.38
     Em
    0.38
     suspended
    0.36
     Orange
    0.36
     Danube
    0.36
     Ow
    0.35
     Understanding
    0.35
     mA
    0.34
    Activations Density 0.002%

    No Known Activations