© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2465
    Prev
    Next
    INDEX
    Explanations

    C code snippets and related syntax

    oai_token-act-pair · gemini-2.0-flash

    code/logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ’
    -0.31
     Anche
    -0.30
    ’-
    -0.30
     castigo
    -0.30
    ’，
    -0.29
     Estaba
    -0.26
    koliv
    -0.26
     marito
    -0.24
    {}/
    -0.24
    「
    -0.24
    POSITIVE LOGITS
    webElementXpaths
    0.86
    AddTagHelper
    0.82
    ThroughAttribute
    0.80
    MigrationBuilder
    0.79
    +#+#
    0.79
    antMatchers
    0.79
    WireFormatLite
    0.78
    endphp
    0.78
    URLException
    0.77
    TagMode
    0.77
    Activations Density 30.621%

    No Known Activations