© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1309
    Prev
    Next
    INDEX
    Explanations

    words or phrases characteristic of marketing and customer service outreach where the person writing emphasizes how they can help 'you' the customer.

    oai_token-act-pair · gemini-2.0-flash

    contact requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     насељу
    -0.75
     متعلقه
    -0.68
     vectorielles
    -0.68
     autorytatywna
    -0.64
     referenties
    -0.63
     '\\;'
    -0.63
     Majefty
    -0.58
    WillAppear
    -0.57
    DockStyle
    -0.56
     quæ
    -0.54
    POSITIVE LOGITS
     so
    0.75
    WriteTagHelper
    0.67
     if
    0.60
     OMITBAD
    0.49
    AddTagHelper
    0.49
     bar
    0.48
     Mon
    0.48
     as
    0.48
     So
    0.47
    agy
    0.47
    Activations Density 1.526%

    No Known Activations