© 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. 4782
    Prev
    Next
    INDEX
    Explanations

    text speaking about political action mostly using first-person pronouns and imperatives

    oai_token-act-pair · gemini-2.0-flash

    terms related to ending or conclusion

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

    to

    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
    bewerken
    -0.68
     juridiques
    -0.67
     noires
    -0.67
    tvguidetime
    -0.66
     województwie
    -0.62
     définiti
    -0.60
     onCreateView
    -0.58
     présidenti
    -0.57
    WebServlet
    -0.57
     mijne
    -0.57
    POSITIVE LOGITS
     end
    0.61
     reverse
    0.59
     useAppContext
    0.59
     ending
    0.56
    ISupport
    0.55
     ends
    0.53
     defeat
    0.52
    Filmografie
    0.52
     stops
    0.52
     defeated
    0.50
    Activations Density 1.682%

    No Known Activations