© 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. 1269
    Prev
    Next
    INDEX
    Explanations

    words related to business, offers or surveys

    oai_token-act-pair · gemini-2.0-flash

    "we" and similar pronouns

    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
    MergeFrom
    -0.66
     AssemblyTitle
    -0.57
    Fordítás
    -0.54
     ModelExpression
    -0.53
     naselje
    -0.52
    Personendaten
    -0.52
    ेशा
    -0.51
    UpdateData
    -0.51
     ✭✭
    -0.50
    ódź
    -0.50
    POSITIVE LOGITS
     we
    2.09
     our
    1.94
    我們
    1.70
    我们
    1.66
     ours
    1.56
    We
    1.48
     We
    1.48
    我們的
    1.41
     chúng
    1.41
     ourselves
    1.36
    Activations Density 4.517%

    No Known Activations