© 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. 7768
    Prev
    Next
    INDEX
    Explanations

    words related to the history or process of physical manufacturing

    oai_token-act-pair · gemini-2.0-flash

    manufacturing and transport

    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
    InjectAttribute
    -1.03
    Personensuche
    -0.65
    ="@+
    -0.61
     MessageBoxIcon
    -0.59
    ValueStyle
    -0.59
    DebuggerNonUser
    -0.59
     DMCA
    -0.59
     الرياضيه
    -0.58
    featureID
    -0.58
     @"/
    -0.58
    POSITIVE LOGITS
     redor
    0.50
    ↘
    0.47
     Confira
    0.46
     channeling
    0.46
    jach
    0.45
     sash
    0.45
    램
    0.45
    Mentions
    0.44
     shores
    0.44
     canais
    0.44
    Activations Density 14.302%

    No Known Activations