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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7149
    Prev
    Next
    INDEX
    Explanations

    words containing the character sequence "ro", "as," "ine", "on", "xy", "ot", "tal", "atri," and "ac"

    oai_token-act-pair · gemini-2.0-flash

    ro

    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
    <bos>
    -2.83
    ↵↵
    -1.11
    '
    -1.05
    2
    -0.92
    1
    -0.88
    3
    -0.87
    4
    -0.80
    ↵
    -0.77
    -
    -0.77
    I
    -0.76
    POSITIVE LOGITS
    .}~\
    1.07
    ^(@)
    1.03
    ientôt
    0.96
    ]='\
    0.96
    ]--;
    0.94
    .}(
    0.92
    elfare
    0.91
    ousands
    0.91
    drawal
    0.90
    ^(@
    0.89
    Activations Density 2.823%

    No Known Activations