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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5184
    Prev
    Next
    INDEX
    Explanations

    the word "range" in proximity to words indicating distribution, scaling, or ordering

    oai_token-act-pair · gemini-2.0-flash

    terms related to diverse range or levels

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

    range

    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
     للاسماء
    -0.75
     '\\;'
    -0.75
     @"/
    -0.73
    LookAnd
    -0.69
    TestingModule
    -0.69
     Wikimedijinoj
    -0.67
    dafx
    -0.66
    principalColumn
    -0.66
    complexContent
    -0.65
    UnusedPrivate
    -0.64
    POSITIVE LOGITS
    CreateInfo
    0.48
    enumii
    0.46
    plots
    0.44
    참고
    0.41
    cras
    0.40
    Открыть
    0.40
     تانيه
    0.40
    scrollY
    0.40
    FXML
    0.39
    őr
    0.39
    Activations Density 6.293%

    No Known Activations