© 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. 9691
    Prev
    Next
    INDEX
    Explanations

    words related to negative situations, news, unfairness, and conflict

    oai_token-act-pair · 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
     fubject
    -0.52
     africaine
    -0.49
     imprimée
    -0.48
     purpoſe
    -0.47
     découver
    -0.47
     calculées
    -0.46
     chrétien
    -0.46
     Preferencias
    -0.46
    ὶ
    -0.45
     virš
    -0.45
    POSITIVE LOGITS
     noDo
    0.60
    DockStyle
    0.59
    тьми
    0.58
    TagMode
    0.58
     مشين
    0.57
    annica
    0.54
     KeyError
    0.54
    {}{}
    0.53
     createSlice
    0.52
     kark
    0.52
    Activations Density 11.450%

    No Known Activations