© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3632
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with political conflict and gun control

    oai_token-act-pair · gemini-2.0-flash

    gun violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     صوتيه
    -0.65
    #+#
    -0.61
    /−
    -0.60
    comings
    -0.60
    holdet
    -0.59
     iconFacebook
    -0.59
    <()>
    -0.59
     daarvoor
    -0.59
    righted
    -0.59
    ="@+
    -0.59
    POSITIVE LOGITS
     AspNetCore
    0.55
    Captor
    0.51
     alternative
    0.45
    理石
    0.44
    ❋
    0.42
    enst
    0.41
     I
    0.41
    iint
    0.41
     saud
    0.41
    alt
    0.41
    Activations Density 14.186%

    No Known Activations