© 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. 9930
    Prev
    Next
    INDEX
    Explanations

    code snippets that include database connection strings

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Local server addresses

    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
     Men
    -0.46
    spartner
    -0.44
     up
    -0.44
     To
    -0.43
     is
    -0.43
     A
    -0.42
     much
    -0.42
     Sche
    -0.42
    WriteTagHelper
    -0.41
     var
    -0.41
    POSITIVE LOGITS
     resourceCulture
    0.82
     myſelf
    0.80
    RegistryLite
    0.79
    Personensuche
    0.78
     AssemblyCulture
    0.77
    URLException
    0.76
     Efq
    0.76
     linkovi
    0.75
     Administrativna
    0.74
     ―――――
    0.74
    Activations Density 0.899%

    No Known Activations