© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12004
    Prev
    Next
    INDEX
    Explanations

    words that contain the letter sequences "ab", "ant", "fic", "hibit", and related letter patterns across multiple languages.

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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>
    -1.51
    '
    -0.51
    ↵↵
    -0.44
    ja
    -0.42
    5
    -0.41
    <
    -0.41
    mişti
    -0.40
    (
    -0.39
     her
    -0.38
    れています
    -0.38
    POSITIVE LOGITS
    躇
    0.76
    etheless
    0.74
    ]--;
    0.73
    babwe
    0.73
     Newswire
    0.72
    multirow
    0.70
    spesies
    0.68
    tvguidetime
    0.68
    __;
    0.67
    adaş
    0.67
    Activations Density 0.842%

    No Known Activations