© 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. 3556
    Prev
    Next
    INDEX
    Explanations

    LaTeX code snippets

    oai_token-act-pair · gemini-2.0-flash

    LaTeX package commands and document structure

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

    LaTeX code

    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
     Efq
    -0.76
     uſed
    -0.65
    RectangleBorder
    -0.63
    InputBorder
    -0.61
     ſtate
    -0.60
     ſever
    -0.57
     houſe
    -0.57
     poffe
    -0.56
     متعلقه
    -0.56
     purpoſe
    -0.56
    POSITIVE LOGITS
    StoryboardSegue
    0.59
    extAlignment
    0.58
    Reparto
    0.52
     snippetHide
    0.48
    contentLoaded
    0.46
    atigable
    0.46
    SFD
    0.46
     ویکی‌پدیای
    0.45
    phère
    0.45
    $​
    0.45
    Activations Density 0.234%

    No Known Activations