© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14393
    Prev
    Next
    INDEX
    Explanations

    references to companies and legal situations.

    oai_token-act-pair · gemini-2.0-flash

    companies

    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
     Companies
    -2.23
     companies
    -2.17
     Company
    -2.16
    Companies
    -2.16
    Company
    -2.14
    company
    -2.05
    companies
    -2.03
    COMPANY
    -2.00
     COMPANY
    -2.00
     company
    -1.99
    POSITIVE LOGITS
    ђу
    0.40
    iov
    0.35
    bParam
    0.33
     LCCN
    0.33
     ostavi
    0.33
    tencent
    0.32
    atro
    0.31
    SupportActionBar
    0.30
    nocache
    0.29
    λέ
    0.29
    Activations Density 1.121%

    No Known Activations