© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3624
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of local small businesses

    oai_token-act-pair · gemini-2.0-flash

    businesses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     business
    -1.80
    business
    -1.66
     Business
    -1.66
    Business
    -1.65
     BUSINESS
    -1.48
    BUSINESS
    -1.35
     busi
    -1.10
     бизнес
    -1.08
     biznes
    -1.05
     negocio
    -1.03
    POSITIVE LOGITS
     مرئيه
    0.71
    complexContent
    0.70
    itinéraire
    0.69
    MLLoader
    0.65
    MigrationBuilder
    0.64
    RepeatedField
    0.60
    енча
    0.59
     calendriers
    0.58
    awaiter
    0.58
     poveznice
    0.57
    Activations Density 6.633%

    No Known Activations