© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7588
    Prev
    Next
    INDEX
    Explanations

    job advertisements that include contact information

    oai_token-act-pair · gemini-2.0-flash

    Code snippets/random text

    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
     متعلقه
    -0.73
    abestanden
    -0.72
    tagHelperRunner
    -0.69
     estekak
    -0.69
    yntaxException
    -0.68
    StructEnd
    -0.68
    resave
    -0.68
    extAlignment
    -0.67
     للاسماء
    -0.66
    ]]>
    -0.65
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.58
    Посилання
    0.43
    ERAL
    0.41
     isKindOfClass
    0.41
    rena
    0.41
    chin
    0.40
    feng
    0.39
    <table>
    0.39
     springfox
    0.39
    riz
    0.39
    Activations Density 1.288%

    No Known Activations