Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6853
    Prev
    Next
    INDEX
    Explanations

    the word "custom"

    oai_token-act-pair · gemini-2.0-flash

    custom

    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
    Cordialement
    -0.86
     a
    -0.84
    Amicalement
    -0.82
    hirts
    -0.79
    esterday
    -0.76
    uests
    -0.75
    intenance
    -0.73
    ^(@)
    -0.73
     his
    -0.72
    })*/
    -0.71
    POSITIVE LOGITS
     Patro
    0.83
     Minato
    0.82
    NU
    0.81
     Doncaster
    0.81
     Vite
    0.80
     bianchi
    0.78
    по
    0.77
     Hereford
    0.77
     Ophelia
    0.75
    uni
    0.75
    Activations Density 2.384%

    No Known Activations