© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9065
    Prev
    Next
    INDEX
    Explanations

    short news articles with dates and locations.

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or phrases

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

    start of articles

    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
     Cek
    -0.56
    modb
    -0.52
    Geografi
    -0.50
    JNI
    -0.50
    ]")]
    -0.50
     MenuView
    -0.50
    pherals
    -0.49
    ()\
    -0.49
     demas
    -0.49
     BrowserModule
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.75
    ⓧ
    0.66
     protoimpl
    0.63
    脚注の使い方
    0.61
     صوتيه
    0.60
     paziente
    0.59
     Վերցված
    0.55
     graisse
    0.55
     ویکی‌پدیا
    0.53
     caduta
    0.53
    Activations Density 3.742%

    No Known Activations