© 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. 13962
    Prev
    Next
    INDEX
    Explanations

    language related to political oppression and terrorism

    oai_token-act-pair · gemini-2.0-flash

    technical terms and concepts

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

    Laws and legislation

    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
    出版年
    -0.69
    posedge
    -0.59
    bado
    -0.58
    帖最后由
    -0.58
    AndEndTag
    -0.57
    存于互联网档案馆
    -0.57
    expandindo
    -0.56
    GRANTED
    -0.55
    ाहरण
    -0.55
    schild
    -0.55
    POSITIVE LOGITS
    MIDDLEWARE
    0.49
     NSCoder
    0.47
    arsenal
    0.44
    Espèce
    0.44
    BackStack
    0.43
     powers
    0.43
    downe
    0.43
     Pasquale
    0.43
    도록
    0.42
    jugend
    0.42
    Activations Density 1.723%

    No Known Activations