© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4325
    Prev
    Next
    INDEX
    Explanations

    words ending in "oductory", "os", or "uced"

    oai_token-act-pair · gemini-2.0-flash

    Introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     IndexPath
    -0.62
    }")]
    -0.62
    __*/
    -0.60
    AutoField
    -0.58
    */].
    -0.56
     ©️
    -0.56
    χρι
    -0.55
    enerys
    -0.54
    تقاوى
    -0.54
    (:,:,
    -0.54
    POSITIVE LOGITS
     introduction
    1.53
     introduce
    1.46
     introduces
    1.41
     introductions
    1.39
     introduced
    1.38
     introducing
    1.38
    introduce
    1.37
    introdu
    1.34
     Introduce
    1.34
    introduced
    1.30
    Activations Density 0.816%

    No Known Activations