© 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. 210961
    Prev
    Next
    INDEX
    Explanations

    word embeddings and vector representations

    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
     gráf
    0.42
    died
    0.41
     Mancini
    0.40
    esam
    0.40
     Edit
    0.39
    olist
    0.39
    末
    0.39
    ıt
    0.38
     イタリア
    0.38
     HIST
    0.38
    POSITIVE LOGITS
     swagger
    0.42
     pragmatic
    0.41
     dread
    0.40
     penis
    0.40
     bunker
    0.39
    房間
    0.38
     huge
    0.38
     taxonomy
    0.38
     ㅎㅎ
    0.38
    打印
    0.38
    Activations Density 0.000%

    No Known Activations