© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12845
    Prev
    Next
    INDEX
    Explanations

    academic publications, including publishers, publication names, and individual authors.

    oai_token-act-pair · gemini-2.0-flash

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    таратура
    -0.52
    ardy
    -0.45
    <bos>
    -0.43
    ardless
    -0.42
     fare
    -0.41
    asiness
    -0.41
    nationality
    -0.40
    𝑚
    -0.40
    зре
    -0.40
    itiert
    -0.39
    POSITIVE LOGITS
     Efq
    0.62
    VersionUID
    0.58
    webElementXpaths
    0.53
    AndEndTag
    0.51
     ویکی‌پدیای
    0.48
     pleaſure
    0.48
    PYX
    0.45
    mybatisplus
    0.45
     MainAxisSize
    0.44
     للاسماء
    0.44
    Activations Density 0.206%

    No Known Activations