© 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. 14329
    Prev
    Next
    INDEX
    Explanations

    words beginning with "sto" or "stool" when they relate to medical or health issues

    oai_token-act-pair · gemini-2.0-flash

    terms related to stool examination or analysis

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

    technical or foreign snippets

    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
    MockMvc
    -0.48
    uq
    -0.41
     kec
    -0.41
     O
    -0.40
     im
    -0.38
     B
    -0.38
     Im
    -0.38
     T
    -0.38
    tabular
    -0.36
     is
    -0.36
    POSITIVE LOGITS
    Personendaten
    0.82
     définiti
    0.77
    RegressionTest
    0.77
     myſelf
    0.73
    RTEE
    0.73
    -------------</
    0.73
     démocr
    0.73
    __':
    0.73
     propOrder
    0.72
     actualité
    0.71
    Activations Density 0.470%

    No Known Activations