© 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. 3619
    Prev
    Next
    INDEX
    Explanations

    words related to taking action to accomplish something

    oai_token-act-pair · gemini-2.0-flash

    communication and integration

    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
     Significant
    -0.81
     Particular
    -0.77
     Specific
    -0.75
     These
    -0.72
     Understanding
    -0.72
     Such
    -0.71
     Untold
    -0.69
     Issues
    -0.69
    Specific
    -0.67
    Significant
    -0.67
    POSITIVE LOGITS
    ⓧ
    0.58
     AssemblyProduct
    0.47
    }{*}{}
    0.46
    DebuggerNonUser
    0.46
    BeginContext
    0.43
    GEBURTSDATUM
    0.43
    DebuggerStep
    0.43
    AutoScaleMode
    0.42
    InjectAttribute
    0.42
     Normdatei
    0.41
    Activations Density 37.450%

    No Known Activations