© 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. 9137
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words related to computing, technical writing discussing options, and chemical analysis.

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    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
     effectively
    -1.45
     efficiently
    -1.39
     correctly
    -1.37
     informally
    -1.35
     permanently
    -1.35
     manually
    -1.34
    correctly
    -1.34
     independently
    -1.31
     Effectively
    -1.31
     properly
    -1.30
    POSITIVE LOGITS
     ligiloj
    0.59
    potranspiration
    0.56
    reprodu
    0.47
    hibe
    0.47
     Ilustra
    0.46
    BIDDEN
    0.46
     дописавши
    0.46
    eachtet
    0.45
    ništ
    0.45
    distan
    0.45
    Activations Density 12.950%

    No Known Activations