© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10341
    Prev
    Next
    INDEX
    Explanations

    tokens having to do with real estate and land management.

    oai_token-act-pair · gemini-2.0-flash

    skin, land, tissue

    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
     comuniques
    -0.63
    ://$
    -0.60
    contentLoaded
    -0.60
    SourceChecksum
    -0.59
    AccessorTable
    -0.57
     الحره
    -0.56
    FunctionFlags
    -0.56
     kasarigan
    -0.55
     '\\;'
    -0.55
     foods
    -0.54
    POSITIVE LOGITS
     land
    1.00
    land
    0.76
     tissue
    0.63
     skin
    0.62
    aarrggbb
    0.58
    LAND
    0.58
     LAND
    0.55
     Land
    0.54
     wire
    0.54
    Land
    0.54
    Activations Density 4.076%

    No Known Activations