© 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. 7410
    Prev
    Next
    INDEX
    Explanations

    what common words appear often together in a relatively small window of text.

    oai_token-act-pair · gemini-2.0-flash

    terms related to threats or danger

    np_token-act-pair-logits · gpt-4o-mini
    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
     <>",
    -0.70
    EDEFAULT
    -0.70
     <=",
    -0.69
     ostavi
    -0.66
    ")));
    -0.63
    ))))))))
    -0.62
     Audiodateien
    -0.62
    AsUp
    -0.61
     HttpNotFound
    -0.61
    <>();
    -0.60
    POSITIVE LOGITS
    RegressionTest
    0.50
    Iden
    0.47
    fer
    0.45
     murderous
    0.44
     bears
    0.44
    protoimpl
    0.43
    InputBorder
    0.43
     dangerous
    0.43
     danger
    0.42
    mtx
    0.42
    Activations Density 1.503%

    No Known Activations