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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4799
    Prev
    Next
    INDEX
    Explanations

    text discussing economic development and county commissioners

    oai_token-act-pair · gemini-2.0-flash

    programming language elements and resources

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

    quotes and attributions

    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
    enumi
    -0.40
    then
    -0.39
    .
    -0.39
     läm
    -0.38
     then
    -0.37
    ,
    -0.36
    月刊
    -0.35
     textes
    -0.35
    occasione
    -0.34
    等
    -0.34
    POSITIVE LOGITS
     lenker
    1.03
     виправивши
    0.92
     resourceCulture
    0.91
    Datuak
    0.85
     HasFactory
    0.84
     дописавши
    0.80
     ProtoMessage
    0.79
    __":
    0.77
     مشين
    0.74
     tartalomajánló
    0.73
    Activations Density 3.146%

    No Known Activations