© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13244
    Prev
    Next
    INDEX
    Explanations

    text related to fighting and competition

    oai_token-act-pair · gemini-2.0-flash

    Mixed martial arts

    np_max-act-logits · gemini-2.0-flash

    mixed martial arts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    uticos
    -0.65
    Autoritní
    -0.59
     botanique
    -0.57
    ArrowToggle
    -0.56
    ViewFeatures
    -0.56
    utilisons
    -0.54
    jednoc
    -0.53
     surla
    -0.53
     disambiguazione
    -0.53
    ⊰
    -0.53
    POSITIVE LOGITS
     self
    0.68
     striking
    0.67
     mixed
    0.65
     Mixed
    0.65
     mu
    0.65
     submission
    0.65
    Self
    0.63
     ju
    0.61
     Self
    0.60
    Mixed
    0.59
    Activations Density 2.726%

    No Known Activations