Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1130
    Prev
    Next
    INDEX
    Explanations

    text discussing entrepreneurialism, business, and education.

    oai_token-act-pair · gemini-2.0-flash

    entrepreneur

    np_token-act-pair-logits · gemini-2.0-flash

    entrepreneur

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    SerializedSize
    -0.52
    StartTag
    -0.47
    aziland
    -0.46
    SizeMode
    -0.45
     orina
    -0.44
     BorderRadius
    -0.44
     ujednoznacz
    -0.44
    etheless
    -0.44
    perties
    -0.44
    gnition
    -0.44
    POSITIVE LOGITS
    evos
    0.64
    GEBURTSDATUM
    0.61
    expandindo
    0.57
    OGND
    0.56
    esModule
    0.52
    Geplaatst
    0.52
     Vra
    0.52
    Melhor
    0.52
     jadx
    0.52
     ytter
    0.52
    Activations Density 8.311%

    No Known Activations