© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2807
    Prev
    Next
    INDEX
    Explanations

    information related to competitive games and rankings, especially chess

    oai_token-act-pair · gemini-2.0-flash

    ratings

    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
    fillable
    -0.47
    ฉ
    -0.47
    Literatura
    -0.47
    ExecuteReader
    -0.45
     cij
    -0.45
    Common
    -0.45
    ništ
    -0.44
    Bel
    -0.42
    Sample
    -0.42
    Con
    -0.42
    POSITIVE LOGITS
     career
    0.68
     purpoſe
    0.63
    rungsseite
    0.60
     perſon
    0.60
    Obrázky
    0.60
     careers
    0.60
    rxjs
    0.58
    astéroïdes
    0.57
    ---*/
    0.57
    RTEX
    0.57
    Activations Density 1.964%

    No Known Activations