© 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. 5036
    Prev
    Next
    INDEX
    Explanations

    connecting words and adjectives that describe an object or action

    oai_token-act-pair · gemini-2.0-flash

    possibility

    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
     AssemblyProduct
    -0.58
    Portail
    -0.58
    setViewportView
    -0.55
    ۪
    -0.52
    ähän
    -0.50
    __(/*!
    -0.50
    ercice
    -0.49
    titleMargin
    -0.49
    uke
    -0.47
    InputElement
    -0.47
    POSITIVE LOGITS
     opportunity
    0.97
     capability
    0.96
    opportunity
    0.90
     capacity
    0.84
     possibility
    0.82
    capability
    0.81
     chance
    0.80
     ability
    0.79
     option
    0.79
     Capability
    0.77
    Activations Density 5.792%

    No Known Activations