© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3983
    Prev
    Next
    INDEX
    Explanations

    language describing nuclear war and natural disasters

    oai_token-act-pair · gemini-2.0-flash

    weapons and bombs

    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
    etur
    -0.51
    <bos>
    -0.50
    enumi
    -0.50
     Frey
    -0.42
     bot
    -0.42
     Tre
    -0.42
    mö
    -0.40
     d
    -0.40
    CrossRef
    -0.40
    flexDirection
    -0.39
    POSITIVE LOGITS
     onOptions
    0.91
     BoxFit
    0.83
     Efq
    0.81
    SourceChecksum
    0.79
    FormTagHelper
    0.77
     Chriftian
    0.75
    CloseOperation
    0.74
    StoryboardSegue
    0.74
    ScopeManager
    0.73
     Jefus
    0.73
    Activations Density 1.042%

    No Known Activations