© 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. 11310
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that seem important to the surrounding discussion

    oai_token-act-pair · gemini-2.0-flash

    technical terms or concepts in data processing

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

    reports

    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
    \{\\
    -0.50
     مرئيه
    -0.50
     متعلقه
    -0.49
    umumkan
    -0.48
     meanwhile
    -0.47
    oltre
    -0.43
     colgantes
    -0.42
     simultaneously
    -0.41
     newInstance
    -0.41
    terung
    -0.41
    POSITIVE LOGITS
     ſche
    0.65
     ſy
    0.63
    rento
    0.63
     transfieras
    0.61
     masses
    0.60
    AntiForgeryToken
    0.60
    KURZBESCHREIBUNG
    0.59
    -${
    0.58
    sthe
    0.58
     kasarigan
    0.57
    Activations Density 4.971%

    No Known Activations