© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10765
    Prev
    Next
    INDEX
    Explanations

    connectors like "to" along with words related to extending or preventing

    oai_token-act-pair · gemini-2.0-flash

    extend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CWE
    -0.66
    kloped
    -0.64
    RenderAtEndOf
    -0.58
    cipated
    -0.57
    IUrlHelper
    -0.55
    Дереккөздер
    -0.55
     oprot
    -0.54
    fetchone
    -0.54
     Schick
    -0.54
    )];
    -0.52
    POSITIVE LOGITS
     extend
    2.59
     extension
    2.55
     extending
    2.53
     extended
    2.44
     extends
    2.34
     Extension
    2.30
     Extending
    2.28
     Extend
    2.27
     extensions
    2.20
    extension
    2.13
    Activations Density 3.186%

    No Known Activations