© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9873
    Prev
    Next
    INDEX
    Explanations

    business-related language that includes a mixture of medical, business, or website terms, alongside contact information

    oai_token-act-pair · gemini-2.0-flash

    contact or business information

    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
     procédures
    -0.58
     peniten
    -0.56
    <bos>
    -0.55
     maternelle
    -0.54
     vectorielles
    -0.52
     elettrica
    -0.51
     umana
    -0.50
    raborty
    -0.50
     françaises
    -0.50
     evaluates
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.84
    oredCriteria
    0.65
    featureID
    0.65
    })`
    0.49
    tagHelperRunner
    0.49
    simpleType
    0.48
    LookAnd
    0.47
     protoimpl
    0.46
     Mini
    0.46
     Tempt
    0.45
    Activations Density 12.520%

    No Known Activations