© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    information about sports, especially baseball

    oai_token-act-pair · gemini-2.0-flash

    start

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ioutil
    -0.49
    ittin
    -0.46
    CopyWith
    -0.46
    extAlignment
    -0.45
    RuleContext
    -0.44
    挂
    -0.43
    AccessorTable
    -0.43
    Etimo
    -0.42
    νω
    -0.42
    ajes
    -0.42
    POSITIVE LOGITS
     start
    3.05
     Start
    2.81
    start
    2.80
    Start
    2.77
     starts
    2.72
     starting
    2.50
     START
    2.45
     Starts
    2.44
     Starting
    2.39
    START
    2.38
    Activations Density 4.435%

    No Known Activations