© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16198
    Prev
    Next
    INDEX
    Explanations

    language related to Christian religious belief, particularly around sacrifice and community.

    oai_token-act-pair · gemini-2.0-flash

    random assortment of topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     initComponents
    -0.74
    didSet
    -0.71
    存于互联网档案馆
    -0.65
    🏾
    -0.60
     ②
    -0.59
    DoubleQuotes
    -0.58
     Vectors
    -0.57
    getSeconds
    -0.56
    MessageTagHelper
    -0.56
     Tch
    -0.55
    POSITIVE LOGITS
    tvguidetime
    0.50
    position
    0.48
    
    0.45
     تانيه
    0.44
     positional
    0.43
    GrantedAuthority
    0.43
    pulumi
    0.41
    gapi
    0.40
     Position
    0.40
     position
    0.40
    Activations Density 1.673%

    No Known Activations