© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5564
    Prev
    Next
    INDEX
    Explanations

    instances of people being shot

    oai_token-act-pair · gemini-2.0-flash

    instances of the word 'shot'

    np_token-act-pair-logits · gpt-4o-mini

    shot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     فريبيس
    -0.79
     MainAxisSize
    -0.77
    djangoproject
    -0.65
    Sucesor
    -0.63
     vnode
    -0.63
     betweenstory
    -0.62
    @[+][
    -0.62
    oa̍t
    -0.62
    IntoConstraints
    -0.60
    IVEREF
    -0.57
    POSITIVE LOGITS
    ⓧ
    0.48
    anat
    0.46
    //
    0.44
     ant
    0.43
    TAN
    0.43
     bili
    0.43
    Ant
    0.43
     initComponents
    0.43
    нар
    0.41
     "}
    0.41
    Activations Density 3.762%

    No Known Activations