© 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. 10591
    Prev
    Next
    INDEX
    Explanations

    short words, particularly prepositions and articles, often in groups.

    oai_token-act-pair · gemini-2.0-flash

    foreign language or untranslated phrases

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

    companies and contracts

    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
     Blouse
    -0.49
    withIdentifier
    -0.47
    initializeApp
    -0.47
    EventBus
    -0.46
     bassin
    -0.46
    subsid
    -0.46
     subsid
    -0.46
     様
    -0.45
    aler
    -0.44
     cuis
    -0.44
    POSITIVE LOGITS
    CURY
    0.64
    󠁢
    0.58
     &___
    0.58
    GEBURTSDATUM
    0.58
    dymyr
    0.56
    Portale
    0.56
    ceus
    0.56
    cipar
    0.54
    تيجة
    0.53
    parsedMessage
    0.52
    Activations Density 0.915%

    No Known Activations