© 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-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11080
    Prev
    Next
    INDEX
    Explanations

    the word "course" and words near it

    oai_token-act-pair · gemini-2.0-flash

    course

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prüche
    -0.50
    gemä
    -0.48
     VIAF
    -0.47
    KEYCODE
    -0.47
    LookAnd
    -0.47
     decompression
    -0.45
    OGND
    -0.44
    バーグ
    -0.44
    MethodManager
    -0.43
     WebDriverWait
    -0.43
    POSITIVE LOGITS
     surla
    0.75
     stringBy
    0.63
    UpInside
    0.59
    tvguidetime
    0.59
    ]=="
    0.54
    MessageOf
    0.54
    istar
    0.53
     arşivlendi
    0.53
    原始内容存档于
    0.53
     发表于
    0.52
    Activations Density 4.112%

    No Known Activations