© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8810
    Prev
    Next
    INDEX
    Explanations

    mentions of "BAHAMAS" or a related date/time

    oai_token-act-pair · gemini-2.0-flash

    Bahamas shark trip

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    o
    -1.05
    er
    -1.04
    a
    -1.00
    es
    -0.96
    en
    -0.91
    an
    -0.90
    ed
    -0.82
    ا
    -0.76
    oe
    -0.76
    oa
    -0.75
    POSITIVE LOGITS
    m
    0.80
    k
    0.74
    n
    0.69
    z
    0.65
    l
    0.64
    d
    0.63
    g
    0.62
    re
    0.62
    ll
    0.61
    nt
    0.58
    Activations Density 7.503%

    No Known Activations