© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14782
    Prev
    Next
    INDEX
    Explanations

    legal and business entities and their descriptors

    oai_token-act-pair · gemini-2.0-flash

    company names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ########.
    -0.78
    tvguidetime
    -0.77
    ]-->
    -0.71
     sandero
    -0.67
     Meksiku
    -0.66
    Datuak
    -0.64
     iprot
    -0.63
    AddTagHelper
    -0.63
     Мексичка
    -0.61
    LookAnd
    -0.60
    POSITIVE LOGITS
     company
    0.74
     companies
    0.72
     firm
    0.71
     компаний
    0.70
     firms
    0.69
    Company
    0.69
    company
    0.68
     Company
    0.68
     perusahaan
    0.68
    companies
    0.66
    Activations Density 1.300%

    No Known Activations