© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7859
    Prev
    Next
    INDEX
    Explanations

    words related to construction and fasteners

    oai_token-act-pair · gemini-2.0-flash

    technical file-related terms

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

    Building and installation

    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
    DataMember
    -0.66
    
    -0.66
    |<\
    -0.60
    ⓧ
    -0.60
    Bronnen
    -0.56
     Reverso
    -0.56
     IBOutlet
    -0.53
    Autoritní
    -0.49
     AssemblyCulture
    -0.48
     않았
    -0.47
    POSITIVE LOGITS
     nakalista
    0.59
    CppMethod
    0.54
    aptation
    0.54
    oday
    0.53
    رشف
    0.52
     ExecuteAsync
    0.52
    gonic
    0.51
    molly
    0.51
    }{*}{}
    0.51
    UDIO
    0.50
    Activations Density 2.762%

    No Known Activations