© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5345
    Prev
    Next
    INDEX
    Explanations

    sentence structure with articles and prepositions that have adjectives or descriptors

    oai_token-act-pair · gemini-2.0-flash

    Scientific or technical explanations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     designers
    -1.84
     writers
    -1.73
     developers
    -1.70
     surgeons
    -1.66
     engineers
    -1.62
     authors
    -1.62
     creators
    -1.61
     Designers
    -1.61
     scientists
    -1.58
     physicians
    -1.58
    POSITIVE LOGITS
     Aprile
    0.47
    IInterface
    0.44
    gnat
    0.41
     initComponents
    0.40
    нови
    0.39
    cob
    0.39
     Fahr
    0.38
    co
    0.38
    ph
    0.37
     TestBed
    0.37
    Activations Density 2.664%

    No Known Activations