© 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. 3225
    Prev
    Next
    INDEX
    Explanations

    angle brackets, quotes, numbers, and comments in code.

    oai_token-act-pair · gemini-2.0-flash

    HTML/XML tags

    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
     ivelany
    -0.98
     bezeichneter
    -0.98
    Personensuche
    -0.96
     كومونز
    -0.95
     utafitiHapana
    -0.92
     Normdatei
    -0.91
    UnsafeEnabled
    -0.91
     ویکی‌پدی
    -0.90
    Geplaatst
    -0.88
    tvguidetime
    -0.88
    POSITIVE LOGITS
    </tbody>
    0.51
    </h4>
    0.51
    <b>
    0.48
    <i>
    0.47
    {{
    0.47
    <code>
    0.47
    ↵↵
    0.46
    %
    0.45
    0.45
    <blockquote>
    0.43
    Activations Density 4.011%

    No Known Activations