© 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. 11497
    Prev
    Next
    INDEX
    Explanations

    code syntax like semicolons

    oai_token-act-pair · gemini-2.0-flash

    coding functions related to tags and attributes

    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
    "])
    -0.59
     ")");
    -0.56
    QUADS
    -0.55
    '])
    -0.55
    ']:
    -0.54
     '.',
    -0.51
    ').
    -0.51
     Hem
    -0.51
     Hard
    -0.50
     hard
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.85
    WriteBarrier
    0.78
     esternos
    0.78
     utafitiHapana
    0.73
    UnsafeEnabled
    0.71
    InjectAttribute
    0.71
     ligiloj
    0.70
    ագրություններ
    0.69
     houſe
    0.68
    tagHelperRunner
    0.66
    Activations Density 1.966%

    No Known Activations