© 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. 14656
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and references to "Australia" in the same context.

    oai_token-act-pair · gemini-2.0-flash

    miscellaneous text snippets

    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
    헌
    -0.57
    setPointSize
    -0.57
     وتسجيلات
    -0.56
    twimg
    -0.56
    الإنجليزية
    -0.55
    balleur
    -0.55
    AsUp
    -0.54
     betweenstory
    -0.54
     Obrador
    -0.53
    +#+
    -0.50
    POSITIVE LOGITS
     >=",
    0.59
    Vtbl
    0.57
     مرئيه
    0.57
    kubectl
    0.56
     AppCompatTheme
    0.56
    -$
    0.56
     Roskov
    0.54
     $
    0.50
     $(
    0.49
    TagHelpers
    0.48
    Activations Density 7.532%

    No Known Activations