© 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. 10718
    Prev
    Next
    INDEX
    Explanations

    sentences describing a person's actions or movements in a narrative

    oai_token-act-pair · gemini-2.0-flash

    terms related to openings or entrances

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

    opening

    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
     betweenstory
    -0.70
     autorytatywna
    -0.54
     dores
    -0.51
    UrlEncoded
    -0.50
     Wikimedijinoj
    -0.50
    WebElementEntity
    -0.50
    GeneratedCode
    -0.47
    ToProps
    -0.46
    Mend
    -0.45
     CP
    -0.45
    POSITIVE LOGITS
    DeleteBehavior
    0.62
     opening
    0.58
    tonsoft
    0.55
     opens
    0.54
     lead
    0.53
     opened
    0.52
    opening
    0.52
    Opening
    0.52
     pronti
    0.51
     ouvrir
    0.50
    Activations Density 0.995%

    No Known Activations