© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3334
    Prev
    Next
    INDEX
    Explanations

    information about baseball players and statistics

    oai_token-act-pair · gemini-2.0-flash

    ERA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     AssemblyCulture
    -0.60
     esternos
    -0.57
    prepareStatement
    -0.57
     AssemblyVersion
    -0.53
    țională
    -0.52
    full
    -0.52
    OrEmpty
    -0.52
    Hochspringen
    -0.51
    digarh
    -0.49
    gjenge
    -0.49
    POSITIVE LOGITS
    ArrowToggle
    0.73
    
    0.69
     snippetHide
    0.63
    protoimpl
    0.62
    zzleHttp
    0.59
     referrerpolicy
    0.54
    openzeppelin
    0.54
    toggler
    0.52
     frets
    0.52
    ApiModelProperty
    0.48
    Activations Density 1.296%

    No Known Activations