Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14369
    Prev
    Next
    INDEX
    Explanations

    words that are often used with superlatives to amplify the description

    oai_token-act-pair · gemini-2.0-flash

    achievements and recognitions

    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
    DockStyle
    -0.82
     للمعارف
    -0.82
    findpost
    -0.80
     ſever
    -0.77
    AnchorStyles
    -0.77
    awtextra
    -0.76
     unknownFields
    -0.75
    onViewCreated
    -0.73
     raiſ
    -0.73
     houſe
    -0.73
    POSITIVE LOGITS
     round
    0.48
     ac
    0.46
     great
    0.44
     vote
    0.42
     Round
    0.41
     W
    0.40
     fab
    0.39
     recognition
    0.39
     credit
    0.39
     зна
    0.38
    Activations Density 1.170%

    No Known Activations