© 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. 6658
    Prev
    Next
    INDEX
    Explanations

    email addresses and related words like "at", "by", "to", "from", and "without"

    oai_token-act-pair · gemini-2.0-flash

    words related to web or programming terms

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

    code and technical snippets

    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
     C
    -0.82
    towej
    -0.57
    RegressionTest
    -0.55
    C
    -0.54
    󠁢
    -0.54
    EditorBrowsable
    -0.53
    ModelSerializer
    -0.53
     CC
    -0.53
    CC
    -0.52
     Cou
    -0.51
    POSITIVE LOGITS
    WebVitals
    0.52
    con
    0.48
    com
    0.45
    OrNil
    0.45
    campal
    0.43
    chaun
    0.43
     depositphotos
    0.42
     conftest
    0.42
     bandung
    0.42
    ección
    0.42
    Activations Density 11.321%

    No Known Activations