© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8111
    Prev
    Next
    INDEX
    Explanations

    words related to automated manufacturing and complex technical workflows

    oai_token-act-pair · gemini-2.0-flash

    technical/academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TargetException
    -0.59
    !';
    -0.59
     NOK
    -0.56
     ddelweddau
    -0.55
    cyklopedia
    -0.54
     للاسماء
    -0.54
     Sicilian
    -0.53
     Paglinawan
    -0.52
     OK
    -0.49
    {}{}
    -0.49
    POSITIVE LOGITS
    ISupport
    0.57
     kasarigan
    0.56
    RefNanny
    0.54
    Espèce
    0.54
    ramienta
    0.53
     Alembic
    0.52
     AUDIT
    0.51
    AutoScale
    0.51
     ویکی‌پدیا
    0.51
    odziel
    0.50
    Activations Density 5.957%

    No Known Activations