© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11449
    Prev
    Next
    INDEX
    Explanations

    words related to leadership and film/TV production

    oai_token-act-pair · gemini-2.0-flash

    leadership and direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.55
    koda
    -0.50
     autorytatywna
    -0.46
    rome
    -0.46
    moveToNext
    -0.45
     useAppContext
    -0.45
     #%
    -0.44
    bilt
    -0.44
    ثیر
    -0.44
    atosis
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.62
    BeginContext
    0.56
    copg
    0.52
    reportWebVitals
    0.52
     personally
    0.52
     certiorari
    0.52
    RenderAtEndOf
    0.52
     ANCHE
    0.51
    лтемелер
    0.50
    AnimationsModule
    0.50
    Activations Density 1.000%

    No Known Activations