© 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. 10541
    Prev
    Next
    INDEX
    Explanations

    numbers, quotes and possessives appearing in stories about businesses and economics

    oai_token-act-pair · gemini-2.0-flash

    say 's word or 0'

    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
    .
    -0.46
    :
    -0.46
     (
    -0.43
    -
    -0.42
     
    -0.41
     Entsch
    -0.40
    ...
    -0.39
     smrti
    -0.37
    ız
    -0.37
    ضو
    -0.37
    POSITIVE LOGITS
    saraba
    1.06
    RegressionTest
    1.02
    SequentialGroup
    1.00
    PyExc
    1.00
     onCancelled
    0.99
    OGND
    0.97
    脚注の使い方
    0.97
     autorytatywna
    0.95
     disambiguazione
    0.92
    MigrationBuilder
    0.91
    Activations Density 0.067%

    No Known Activations