© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5971
    Prev
    Next
    INDEX
    Explanations

    technical documentation about industrial networking

    oai_token-act-pair · gemini-2.0-flash

    technical jargon

    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
     MainAxisSize
    -0.87
     تضيفلها
    -0.75
     Italijanski
    -0.71
    colgroup
    -0.65
    IsContent
    -0.63
    Vidite
    -0.62
     beginnetje
    -0.61
    esgue
    -0.58
     لينك
    -0.57
     препратки
    -0.56
    POSITIVE LOGITS
    UIImageView
    0.62
    rhein
    0.58
    vivencia
    0.57
    æus
    0.55
     Mejía
    0.52
     méri
    0.52
    cuerdo
    0.52
    ByPrimaryKey
    0.52
     secoli
    0.50
    ercito
    0.50
    Activations Density 9.924%

    No Known Activations