© 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. 13111
    Prev
    Next
    INDEX
    Explanations

    code snippets with javascript and html tags

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with letters G, S, T

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

    code

    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
     betweenstory
    -1.34
    styleType
    -1.09
     InputDecoration
    -1.02
     CreateTagHelper
    -1.02
     Theſe
    -0.94
     itſelf
    -0.94
     ſind
    -0.93
     doubtnut
    -0.93
    Демографія
    -0.93
    stateProvider
    -0.93
    POSITIVE LOGITS
     G
    0.64
     S
    0.59
     T
    0.59
     (
    0.58
    S
    0.55
    G
    0.54
     Z
    0.54
    ↵↵
    0.51
    /
    0.51
    as
    0.51
    Activations Density 2.166%

    No Known Activations