© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13685
    Prev
    Next
    INDEX
    Explanations

    words related to business management positions and responsibilities.

    oai_token-act-pair · gemini-2.0-flash

    Business/leadership

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     jScrollPane
    -0.76
    ########.
    -0.71
    featureID
    -0.71
    parsedMessage
    -0.70
    PreferredItem
    -0.68
    thâu
    -0.67
    potranspiration
    -0.65
    findpost
    -0.65
    tubers
    -0.65
    estars
    -0.64
    POSITIVE LOGITS
    korb
    0.52
    pann
    0.48
    wohner
    0.47
    Vice
    0.46
     thought
    0.46
     inferiores
    0.45
     Mauer
    0.43
    yer
    0.42
     Unters
    0.42
     Knuckles
    0.41
    Activations Density 2.300%

    No Known Activations