© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4457
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports and betting

    oai_token-act-pair · gemini-2.0-flash

    Sports betting/finance

    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
    VolleyError
    -0.54
    vités
    -0.52
     relâche
    -0.49
    ่าย
    -0.48
    AttributeSet
    -0.48
    arquía
    -0.47
     rayures
    -0.47
     vescovo
    -0.47
    ToMany
    -0.46
     coloridas
    -0.46
    POSITIVE LOGITS
    complexContent
    0.75
    expandindo
    0.72
    TargetException
    0.63
    gatsby
    0.59
    flexDirection
    0.58
     дописавши
    0.57
     '{@
    0.56
     pleaſure
    0.55
    ırl
    0.55
     againſt
    0.54
    Activations Density 0.489%

    No Known Activations