© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6536
    Prev
    Next
    INDEX
    Explanations

    HTML line breaks, paragraph tags and heading tags

    oai_token-act-pair · gemini-2.0-flash

    br

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     تضيفلها
    -1.49
    ^(@)
    -1.38
     $_"
    -1.33
     '\\;'
    -1.20
     Efq
    -1.19
    ICAGO
    -1.17
    ValueStyle
    -1.16
     Monfieur
    -1.13
     ―――――
    -1.13
     defaultstate
    -1.13
    POSITIVE LOGITS
    <em>
    1.00
    2
    0.99
    1
    0.97
    <eos>
    0.97
    <strong>
    0.92
    3
    0.90
    <h2>
    0.89
    0
    0.88
    p
    0.85
    ,
    0.84
    Activations Density 0.206%

    No Known Activations