© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    words that indicate research citations and results

    oai_token-act-pair · gemini-2.0-flash

    Academic writing

    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
    TagMode
    -0.85
     ModelRenderer
    -0.72
     مرئيه
    -0.70
    IntoConstraints
    -0.68
    ContentAlignment
    -0.68
     BoxFit
    -0.66
    aarrggbb
    -0.65
    ArrowToggle
    -0.59
    ValueStyle
    -0.58
    Демографія
    -0.58
    POSITIVE LOGITS
     preuves
    0.51
    épreuve
    0.48
     steder
    0.47
     bonté
    0.46
    cedido
    0.45
     tả
    0.43
     formulating
    0.43
     femininas
    0.42
     résult
    0.42
    теристика
    0.42
    Activations Density 24.638%

    No Known Activations