© 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. 6630
    Prev
    Next
    INDEX
    Explanations

    mentions of Korean historical figures and places, some Japanese historical eras, and mentions of death.

    oai_token-act-pair · gemini-2.0-flash

    terms related to geographical locations and historical references

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

    historical contexts

    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
    المشاركات
    -0.52
    setDo
    -0.47
    apimachinery
    -0.45
    äki
    -0.45
    EndContext
    -0.44
     tả
    -0.44
    initComponents
    -0.44
     Rek
    -0.44
     brancas
    -0.43
     ske
    -0.43
    POSITIVE LOGITS
     Bioaccumulative
    0.67
    Referências
    0.59
    MigrationBuilder
    0.52
    tisgarh
    0.51
    Legături
    0.51
    帖最后由
    0.51
    providedIn
    0.49
    picasso
    0.49
    laq
    0.49
    ولة
    0.48
    Activations Density 1.437%

    No Known Activations