© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11923
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and nouns related to sports and competition

    oai_token-act-pair · gemini-2.0-flash

    sports teams/players

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -1.02
    setVerticalGroup
    -0.88
     CreateTagHelper
    -0.86
    ftagPool
    -0.77
    ViewFeatures
    -0.77
    enterOuterAlt
    -0.74
    <tfoot>
    -0.73
    RenderAtEndOf
    -0.73
    évaluateur
    -0.72
    EndContext
    -0.71
    POSITIVE LOGITS
     unit
    0.52
    üyü
    0.47
    unit
    0.42
    angg
    0.41
    >-</
    0.40
    Unit
    0.40
    Saludos
    0.40
    ">−
    0.40
    ölf
    0.40
     hands
    0.39
    Activations Density 0.624%

    No Known Activations