© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    technical writing, specifically relating to the medical studies, arithmetic and computer architecture.

    oai_token-act-pair · gemini-2.0-flash

    exceptions and context

    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
     greater
    -2.66
    greater
    -2.56
    Greater
    -2.34
     Greater
    -2.13
     greatest
    -1.84
    greatest
    -1.73
    GREATER
    -1.55
     Greatest
    -1.45
    Greatest
    -1.39
     greate
    -1.12
    POSITIVE LOGITS
     متعلقه
    0.71
    ImageContext
    0.64
    WebElementEntity
    0.63
     चीज़ों
    0.63
    ējās
    0.61
    verifyException
    0.60
     Walkover
    0.58
     '\\;'
    0.56
    UrlResolution
    0.56
     VizieR
    0.55
    Activations Density 10.212%

    No Known Activations