© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6772
    Prev
    Next
    INDEX
    Explanations

    language that speaks to the reader, using "you" a lot, and discussing how to help them with something.

    oai_token-act-pair · gemini-2.0-flash

    your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ']],
    -0.49
     meille
    -0.44
    }}},
    -0.41
     conmigo
    -0.40
     définiti
    -0.39
    рін
    -0.38
    gel
    -0.38
    atother
    -0.37
     panier
    -0.36
    '}>
    -0.36
    POSITIVE LOGITS
     your
    1.51
    your
    1.20
    tagHelperRunner
    1.06
    Your
    1.02
     Your
    1.02
     YOUR
    0.96
    YOUR
    0.92
     вашим
    0.89
     votre
    0.89
     ваших
    0.87
    Activations Density 1.568%

    No Known Activations