© 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. 8250
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and web requests

    oai_token-act-pair · gemini-2.0-flash

    response

    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
    <bos>
    -0.71
     the
    -0.54
     file
    -0.51
    .
    -0.50
     access
    -0.47
     an
    -0.47
     and
    -0.46
     string
    -0.45
     key
    -0.44
     text
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    1.11
    igshid
    1.05
    interopRequire
    1.02
     combineReducers
    0.99
     مشين
    0.98
     يتيمه
    0.97
    parsedMessage
    0.95
     snippetHide
    0.94
     springfox
    0.94
    CopyWith
    0.94
    Activations Density 0.946%

    No Known Activations