© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6808
    Prev
    Next
    INDEX
    Explanations

    the word "witness" and sometimes nearby words

    oai_token-act-pair · gemini-2.0-flash

    witness

    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
     avoient
    -0.87
     ainfi
    -0.84
     dévelo
    -0.84
     pouvoit
    -0.82
     feroit
    -0.82
     Проци
    -0.77
     auroit
    -0.76
     auffi
    -0.76
    ñora
    -0.75
     religieuses
    -0.75
    POSITIVE LOGITS
    providedIn
    1.05
    UIControlState
    0.91
    AddTagHelper
    0.88
    awtextra
    0.85
     BorderRadius
    0.84
    icap
    0.82
    numerusform
    0.82
    webElementXpaths
    0.81
    InputBorder
    0.80
    IUrlHelper
    0.79
    Activations Density 1.815%

    No Known Activations