© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4915
    Prev
    Next
    INDEX
    Explanations

    technical writing about bones, especially bone density and screws

    oai_token-act-pair · gemini-2.0-flash

    bones

    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
     bone
    -2.03
     Bone
    -2.03
    Bone
    -1.87
    bone
    -1.86
     bones
    -1.80
    bones
    -1.74
    BONE
    -1.72
     Bones
    -1.71
    Bones
    -1.51
    骨
    -1.46
    POSITIVE LOGITS
     ddelweddau
    0.65
     nahilalakip
    0.60
     AssemblyCulture
    0.59
    ollectionView
    0.59
    Посилання
    0.56
    ftagPool
    0.51
    tahui
    0.50
     Dominion
    0.47
     ImportError
    0.46
    Personensuche
    0.46
    Activations Density 1.704%

    No Known Activations