© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176003
    Prev
    Next
    INDEX
    Explanations

    calm, soothing, or approach slowly

    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_20_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
     legen
    0.38
    handmade
    0.37
     sporadic
    0.36
    ❾
    0.36
    IGER
    0.36
     sputum
    0.35
    rtel
    0.35
     chorizo
    0.35
     inflamm
    0.35
     보고
    0.35
    POSITIVE LOGITS
    词
    0.33
    恋
    0.33
    心理
    0.32
    ăng
    0.31
     Calvin
    0.31
    命令
    0.31
     Jacoby
    0.30
    缝
    0.30
    追
    0.30
    ونها
    0.29
    Activations Density 0.018%

    No Known Activations