© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8307
    Prev
    Next
    INDEX
    Explanations

    words related to software code

    oai_token-act-pair · gemini-2.0-flash

    code properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.82
    <bos>
    -0.80
    ’
    -0.59
    '
    -0.58
    ↵
    -0.54
    WebServlet
    -0.49
    "]]
    -0.47
    "]).
    -0.46
     was
    -0.45
    FormTagHelper
    -0.45
    POSITIVE LOGITS
    igshid
    0.73
     Mitar
    0.73
    PerformLayout
    0.72
     wikipagina
    0.72
    EndProject
    0.71
     Theaters
    0.67
    roscope
    0.67
    ArgsConstructor
    0.67
    EndInit
    0.66
    Externé
    0.66
    Activations Density 2.115%

    No Known Activations