© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3709
    Prev
    Next
    INDEX
    Explanations

    the string "Mat" possibly indicating a citation or reference

    oai_token-act-pair · gemini-2.0-flash

    the term "Matplotlib"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ModelAdmin
    -0.54
    wpi
    -0.51
     MonoBehaviour
    -0.51
    Clik
    -0.47
     disambiguazione
    -0.47
    তথ্যসূত্র
    -0.46
     UnityEngine
    -0.45
    theria
    -0.45
    Bodies
    -0.45
    zilla
    -0.44
    POSITIVE LOGITS
    AutoScale
    0.77
    ⓧ
    0.71
    KURZBESCHREIBUNG
    0.71
    WebVitals
    0.59
    NameInMap
    0.56
    expandindo
    0.56
     saites
    0.55
    bootstrapcdn
    0.53
     Thors
    0.53
    Diweddarwch
    0.52
    Activations Density 0.360%

    No Known Activations