© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3866
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and if they are going out of business or changing.

    oai_token-act-pair · gemini-2.0-flash

    business

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nakalista
    -0.65
     chaude
    -0.63
    LabelTagHelper
    -0.57
    GIVEREF
    -0.56
    nlm
    -0.54
    :✨
    -0.53
    bootstrapcdn
    -0.52
    >{@
    -0.52
    itinéraire
    -0.51
    ::__
    -0.51
    POSITIVE LOGITS
     business
    3.34
    business
    2.89
    Business
    2.64
     Business
    2.64
     BUSINESS
    2.48
    BUSINESS
    2.30
     busi
    1.93
     bisnis
    1.87
     biznes
    1.84
     negocio
    1.81
    Activations Density 1.905%

    No Known Activations