© 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. 11418
    Prev
    Next
    INDEX
    Explanations

    references to legislation or government acts

    oai_token-act-pair · gemini-2.0-flash

    legal terminology related to acts and offences

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

    Act

    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
     الرياضيه
    -0.68
    曖昧さ回避
    -0.64
     kasarigan
    -0.63
    rizona
    -0.62
    UTERS
    -0.59
     Alquiler
    -0.57
    RenderAtEndOf
    -0.57
    AntiForgeryToken
    -0.57
     विश्वसनीयता
    -0.57
     auroit
    -0.56
    POSITIVE LOGITS
    andExpect
    0.52
     Cap
    0.52
     point
    0.51
    AddHtmlAttribute
    0.51
     CAP
    0.51
     of
    0.50
    cepts
    0.49
     cap
    0.48
     Classical
    0.48
     Erhaltung
    0.47
    Activations Density 10.060%

    No Known Activations