© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3060
    Prev
    Next
    INDEX
    Explanations

    snippets of HTML table code

    oai_token-act-pair · gemini-2.0-flash

    HTML table elements or tags

    np_token-act-pair-logits · gpt-4o-mini

    HTML table elements

    np_max-act-logits · gemini-2.0-flash
    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
    SourceChecksum
    -0.67
     initComponents
    -0.57
     Roskov
    -0.52
     تضيفلها
    -0.49
    Παραπομπές
    -0.49
     виправивши
    -0.48
     المعيارى
    -0.48
     خارجية
    -0.46
    差し
    -0.45
    reactstrap
    -0.44
    POSITIVE LOGITS
     Col
    0.56
    enterOuterAlt
    0.54
     ProtoMessage
    0.54
    TintMode
    0.54
    Col
    0.53
    LoadScene
    0.53
    batore
    0.52
     intStringLen
    0.51
    windowFixed
    0.51
    col
    0.50
    Activations Density 0.644%

    No Known Activations