© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6335
    Prev
    Next
    INDEX
    Explanations

    words related to construction and building materials

    oai_token-act-pair · gemini-2.0-flash

    tech-related terms or code identifiers

    np_token-act-pair-logits · gpt-4o-mini

    manufacturing and materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ractable
    -0.53
     Kto
    -0.53
    apunov
    -0.51
    Trunk
    -0.50
    примеча
    -0.50
    ViewFeatures
    -0.49
    __":
    -0.48
    AnchorStyles
    -0.47
    ifred
    -0.46
     chirurg
    -0.45
    POSITIVE LOGITS
    MessageTagHelper
    0.66
     isComment
    0.59
     فريبيس
    0.57
     MaterialApp
    0.56
     pigmented
    0.54
    GeneratedCode
    0.54
    unesse
    0.54
    TabIndex
    0.53
    ItemBackground
    0.52
    routs
    0.51
    Activations Density 1.313%

    No Known Activations