© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11580
    Prev
    Next
    INDEX
    Explanations

    negative language and swear words

    oai_token-act-pair · gemini-2.0-flash

    insults/swearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    vated
    -0.72
    GraphicsUnit
    -0.71
    ьаж
    -0.68
    CppCodeGen
    -0.68
    ValueStyle
    -0.65
    InputBorder
    -0.62
    KommentareTeilen
    -0.59
     postIndex
    -0.59
    SequentialGroup
    -0.59
     Exactos
    -0.56
    POSITIVE LOGITS
    FUCK
    0.60
     idiot
    0.60
     morons
    0.60
     bastard
    0.59
     moron
    0.58
    🖕
    0.57
     idiots
    0.57
     fucks
    0.57
     bastards
    0.57
     asshole
    0.56
    Activations Density 0.341%

    No Known Activations