© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4592
    Prev
    Next
    INDEX
    Explanations

    a word stem "lle" or "ull" and the word "Slemish". That's not the best description, so here are some alternatives: Irish geography terms, words with the ully suffix, certain surnames

    oai_token-act-pair · gemini-2.0-flash

    Slemish Mountain, user "dspillett"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    hastly
    -2.08
    oodoo
    -2.02
    ientôt
    -2.02
    ugeot
    -2.00
    ázaro
    -1.96
    limsy
    -1.88
    âteau
    -1.84
    iddhar
    -1.81
    élène
    -1.77
    idalgo
    -1.77
    POSITIVE LOGITS
    out
    0.84
    url
    0.82
    any
    0.82
    its
    0.79
    add
    0.79
    one
    0.78
    org
    0.77
    ary
    0.77
    ini
    0.77
    use
    0.75
    Activations Density 4.476%

    No Known Activations