© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 725
    Prev
    Next
    INDEX
    Explanations

    code-related words and syntax

    oai_token-act-pair · gemini-2.0-flash

    use/using

    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
    <strong>
    -0.47
    <em>
    -0.40
     (
    -0.38
    ’
    -0.38
    '
    -0.36
    <b>
    -0.35
     bija
    -0.35
    -
    -0.35
     पर
    -0.35
    <i>
    -0.35
    POSITIVE LOGITS
     kasarigan
    1.46
     betweenstory
    1.18
     propOrder
    1.16
     BrowserModule
    1.14
     ―――――
    1.14
     $_"
    1.13
     resourceCulture
    1.12
     photolibrary
    1.09
     Efq
    1.07
     Forumite
    1.05
    Activations Density 11.277%

    No Known Activations