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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10070
    Prev
    Next
    INDEX
    Explanations

    words that relate to business-related conversations, marketing, management, and creative ownership

    oai_token-act-pair · gemini-2.0-flash

    construction and related fields

    np_token-act-pair-logits · gpt-4o-mini

    Construction industry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    VIAF
    -0.53
    AccessorTable
    -0.47
    енча
    -0.44
    getDescriptor
    -0.41
    retz
    -0.41
     Reverso
    -0.40
    例句
    -0.38
    Задача
    -0.38
    HideFlags
    -0.37
     geçir
    -0.36
    POSITIVE LOGITS
     construction
    1.03
     Construction
    0.92
     CONSTRUCTION
    0.88
    construction
    0.88
     consulting
    0.86
    CONSTRUCTION
    0.84
     engineering
    0.84
    Construction
    0.82
     >=",
    0.82
     contracting
    0.81
    Activations Density 1.836%

    No Known Activations