© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7261
    Prev
    Next
    INDEX
    Explanations

    content related to sports games and elections, including scores, victories, and comebacks

    oai_token-act-pair · gemini-2.0-flash

    win or defeat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    GIVEREF
    -0.61
    ⌋
    -0.56
    ]")]
    -0.56
    Datuak
    -0.56
    AddTagHelper
    -0.55
     виправивши
    -0.55
    hots
    -0.54
     hashCode
    -0.53
    ">)</
    -0.52
    Consumes
    -0.51
    POSITIVE LOGITS
     victory
    1.69
     win
    1.43
     defeat
    1.34
     victories
    1.32
    victory
    1.28
    Victory
    1.23
     Victory
    1.23
     wins
    1.22
     victoire
    1.18
    win
    1.13
    Activations Density 0.967%

    No Known Activations