© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    the import statements and java code segments

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords or commands

    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
    фе
    -0.37
    cose
    -0.36
    ns
    -0.36
    iences
    -0.36
    index
    -0.36
    cas
    -0.35
     hij
    -0.35
    li
    -0.35
    nia
    -0.35
    ational
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.83
     تانيه
    0.82
     سكانية
    0.82
    IsMutable
    0.78
    AddTagHelper
    0.77
     Efq
    0.77
     bezeichneter
    0.77
     تضيفلها
    0.76
    verwijspagina
    0.76
     itſelf
    0.76
    Activations Density 0.397%

    No Known Activations