© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12471
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to people leaving positions or companies, whether voluntary or involuntary

    oai_token-act-pair · gemini-2.0-flash

    stepping down

    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
    unregister
    -0.56
    FieldNumber
    -0.52
    "]]
    -0.52
    ])){
    -0.52
     zvuky
    -0.50
    pendium
    -0.50
    таратура
    -0.50
    )$}
    -0.50
     createSlice
    -0.50
    Lugares
    -0.49
    POSITIVE LOGITS
    openqa
    0.51
    }:${
    0.47
     Letras
    0.47
     Desta
    0.47
    المناصب
    0.46
     '\\;'
    0.46
     stedet
    0.46
     Desarrollo
    0.46
    AndPassword
    0.46
     aank
    0.45
    Activations Density 13.165%

    No Known Activations