© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8400
    Prev
    Next
    INDEX
    Explanations

    park and recreational amenities

    oai_token-act-pair · gemini-2.0-flash

    outdoor activities/structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     purpoſe
    -0.82
     disambiguazione
    -0.76
    ChildScrollView
    -0.74
     ſtate
    -0.71
    quelize
    -0.70
    addCriterion
    -0.67
     HasFactory
    -0.66
    bootstrapcdn
    -0.64
     Majefty
    -0.62
    ſelves
    -0.61
    POSITIVE LOGITS
     ""],
    0.49
    ISupport
    0.45
    pak
    0.45
     pack
    0.43
    _;
    0.43
     h
    0.41
     AssemblyCulture
    0.41
     pak
    0.41
     PILOT
    0.40
     Shelf
    0.40
    Activations Density 1.641%

    No Known Activations