© 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. 5520
    Prev
    Next
    INDEX
    Explanations

    language selling a product and speaking about the customer

    oai_token-act-pair · gemini-2.0-flash

    you

    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
    enderror
    -0.67
    ever
    -0.61
     BoxDecoration
    -0.54
    *************/
    -0.54
    AddTagHelper
    -0.54
    ｀)
    -0.53
    ｀*)
    -0.53
     realized
    -0.53
    enido
    -0.52
    AddHtmlAttribute
    -0.52
    POSITIVE LOGITS
     towers
    0.63
     ISNI
    0.54
     Towers
    0.54
     backs
    0.52
    ruptedException
    0.50
    Sklici
    0.50
    Glej
    0.50
     extradition
    0.50
     scalars
    0.49
    algebras
    0.47
    Activations Density 8.492%

    No Known Activations