© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10544
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and words associated with opinion and personal narratives.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming keywords

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

    forum posts

    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
    ⓧ
    -0.55
     — 
    -0.50
    jonen
    -0.49
     + 
    -0.48
    **.
    -0.47
    .”—
    -0.47
    StreetMap
    -0.47
    发表于
    -0.46
    .”.
    -0.46
    *',
    -0.46
    POSITIVE LOGITS
    expandindo
    1.02
     saites
    0.67
    AddTagHelper
    0.61
    RemoveField
    0.58
    ecake
    0.57
    ็จ
    0.56
    Datuak
    0.56
     chev
    0.54
    contentLoaded
    0.54
    appcompat
    0.53
    Activations Density 3.633%

    No Known Activations