© 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. 12098
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of words relating to sexual acts, angry speech, social media and legal processes.

    oai_token-act-pair · gemini-2.0-flash

    cursing and negative sentiment

    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
    <bos>
    -0.56
    tagHelperRunner
    -0.51
    '
    -0.50
    gpl
    -0.48
     tweeted
    -0.47
     mon
    -0.46
    localctx
    -0.43
    Personensuche
    -0.43
    ’
    -0.43
    ⓧ
    -0.41
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.75
    AutoScale
    0.69
     مرئيه
    0.65
     wikipagina
    0.64
    ITERATURE
    0.63
     оригіналу
    0.61
     élo
    0.60
    APOLIS
    0.60
    исленность
    0.59
     onCreateView
    0.59
    Activations Density 17.000%

    No Known Activations