© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    mentions of the Freedom of Information act or similar concepts

    oai_token-act-pair · gemini-2.0-flash

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    KommentareTeilen
    -0.54
    formik
    -0.50
    ɵɵ
    -0.49
     vitae
    -0.48
     torchvision
    -0.48
     diec
    -0.46
    LOTTE
    -0.46
     SwiftUI
    -0.46
    rlrl
    -0.45
    Aftermath
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.69
    adpleegd
    0.65
    RenderAtEndOf
    0.65
     tartalomajánló
    0.63
    suje
    0.62
     imageNamed
    0.62
    entery
    0.60
    쨌
    0.60
    CPtr
    0.60
    jmniej
    0.58
    Activations Density 1.182%

    No Known Activations