© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2758
    Prev
    Next
    INDEX
    Explanations

    words which might appear on a business's service menu

    oai_token-act-pair · gemini-2.0-flash

    business services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Portale
    -0.93
    rrggbb
    -0.91
    rungsseite
    -0.90
    Personendaten
    -0.89
     Италијани
    -0.77
    NameInMap
    -0.77
     مشين
    -0.75
    exels
    -0.73
    Personensuche
    -0.72
    UnsafeEnabled
    -0.71
    POSITIVE LOGITS
     mesma
    0.48
     mismos
    0.46
     même
    0.45
     note
    0.45
     mesmo
    0.44
     stesso
    0.44
    reszcie
    0.44
    gar
    0.43
    ņas
    0.43
    note
    0.43
    Activations Density 40.692%

    No Known Activations