© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12735
    Prev
    Next
    INDEX
    Explanations

    code structures and keywords such as case statements and parentheses

    oai_token-act-pair · gemini-2.0-flash

    numbers or numerical identifiers

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

    Code snippets

    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
     חיצוניים
    -1.23
    expandindo
    -1.09
     ModelExpression
    -1.06
    UserScript
    -1.06
     صوتيه
    -1.04
    
    -1.02
     estekak
    -1.02
    ]")]
    -1.01
    InjectAttribute
    -0.98
     CreateTagHelper
    -0.98
    POSITIVE LOGITS
    1
    0.60
     culturali
    0.53
    2
    0.52
    The
    0.50
    [
    0.48
    7
    0.47
    3
    0.46
    5
    0.45
    A
    0.45
    0
    0.45
    Activations Density 5.434%

    No Known Activations