© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    code snippets defining GUI element styles

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming and markup

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

    Foreign words

    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
     size
    -0.48
     sizes
    -0.47
    kennen
    -0.46
    kü
    -0.46
    Tags
    -0.46
    size
    -0.45
    oir
    -0.45
    Gön
    -0.44
    pencer
    -0.42
    anae
    -0.41
    POSITIVE LOGITS
    expandindo
    0.75
    الإنجليزية
    0.71
    WriteTagHelper
    0.68
     armées
    0.66
     devoirs
    0.65
    μιουργ
    0.63
    +#+
    0.62
     vectorielle
    0.59
     horaires
    0.59
     souten
    0.59
    Activations Density 0.120%

    No Known Activations