© 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
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260198
    Prev
    Next
    INDEX
    Explanations

    Python/XML element and attribute names

    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_22_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
    amsu
    0.42
     tâche
    0.37
     airing
    0.36
    透露
    0.36
     Study
    0.35
     Chatter
    0.35
    ⇑
    0.34
    ちゃん
    0.34
     Studie
    0.34
    setLevel
    0.33
    POSITIVE LOGITS
    left
    0.38
     בצ
    0.36
    vvvert
    0.36
     remnant
    0.35
    sta
    0.35
     remnants
    0.35
    撗
    0.35
     subcut
    0.35
    命令
    0.34
     ক্রী
    0.34
    Activations Density 0.016%

    No Known Activations