© 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. 3368
    Prev
    Next
    INDEX
    Explanations

    C++ code related to 3D vectors and vertex properties like UV coordinates, normals, and color

    oai_token-act-pair · gemini-2.0-flash

    non-English language words or phrases

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

    code

    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
    OGND
    -0.82
    Personensuche
    -0.72
    ViewFeatures
    -0.71
    DoubleQuotes
    -0.71
    Personendaten
    -0.70
    DebuggerNonUser
    -0.69
    oa̍t
    -0.69
    Explicación
    -0.66
     насељу
    -0.60
    lapsingToolbar
    -0.59
    POSITIVE LOGITS
     kasar
    0.45
     bun
    0.43
     Wiktionnaire
    0.41
    ómicas
    0.40
    締め
    0.40
    od
    0.40
     nở
    0.40
    不下
    0.39
     mouseClicked
    0.39
    inten
    0.39
    Activations Density 0.693%

    No Known Activations