© 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. 3525
    Prev
    Next
    INDEX
    Explanations

    language related to baseball, especially particular named players

    oai_token-act-pair · gemini-2.0-flash

    Baseball game descriptions

    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
     Waray
    -0.69
     محفوظة
    -0.68
     chimiques
    -0.55
    principalColumn
    -0.55
     виправивши
    -0.55
     InputDecoration
    -0.55
     mérit
    -0.54
     randomization
    -0.53
     argparse
    -0.52
    Specialist
    -0.52
    POSITIVE LOGITS
    ValueStyle
    0.60
    GetAxis
    0.59
    addCriterion
    0.57
    tesy
    0.56
    >*/
    0.49
    scrollY
    0.45
    куда
    0.45
     attend
    0.45
    lacement
    0.44
     Auge
    0.43
    Activations Density 3.356%

    No Known Activations