© 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. 6341
    Prev
    Next
    INDEX
    Explanations

    articles and words describing order or sequence

    oai_token-act-pair · gemini-2.0-flash

    tokens in multiple languages or special characters

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

    the

    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
     a
    -0.55
    a
    -0.46
    A
    -0.44
    From
    -0.42
     an
    -0.42
    oOo
    -0.39
    many
    -0.39
    S
    -0.39
    Several
    -0.38
    ībā
    -0.36
    POSITIVE LOGITS
    tagext
    0.96
    تقاوى
    0.90
    出版年
    0.84
     kasarigan
    0.84
     مشين
    0.78
     виправивши
    0.77
    ########.
    0.77
    Cyfeiriadau
    0.76
    /******/
    0.76
    期刊论文
    0.76
    Activations Density 3.909%

    No Known Activations