© 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. 8125
    Prev
    Next
    INDEX
    Explanations

    C# code snippets related to database queries

    oai_token-act-pair · gemini-2.0-flash

    singular and specific queries

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

    Code snippets

    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
    tagHelperRunner
    -0.63
    testify
    -0.60
    Ț
    -0.56
    BackPressed
    -0.55
    StoryboardSegue
    -0.55
    UnknownFields
    -0.54
    ulario
    -0.54
    \{\\
    -0.53
     المعيارى
    -0.53
     UnityEditor
    -0.51
    POSITIVE LOGITS
     single
    0.65
     Single
    0.64
    Single
    0.64
     Where
    0.63
    Where
    0.60
    Портал
    0.57
    single
    0.56
    下载附件
    0.55
    tonsoft
    0.52
     Served
    0.50
    Activations Density 0.488%

    No Known Activations