© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5656
    Prev
    Next
    INDEX
    Explanations

    US states and locations

    oai_token-act-pair · gemini-2.0-flash

    locations and geographic names

    np_token-act-pair-logits · gpt-4o-mini

    state abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     GenerationType
    -0.73
    первых
    -0.66
    ArrowToggle
    -0.65
     Umständen
    -0.56
    edoria
    -0.55
    amerikanischer
    -0.55
     igång
    -0.54
     stället
    -0.52
    jillo
    -0.52
     citoy
    -0.52
    POSITIVE LOGITS
    ,
    0.58
     createStore
    0.54
    .
    0.51
     hang
    0.49
    исленность
    0.47
    rawQuery
    0.46
    mapView
    0.46
    slidesToShow
    0.45
    bibliothek
    0.44
    Inflater
    0.44
    Activations Density 2.120%

    No Known Activations