© 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. 10832
    Prev
    Next
    INDEX
    Explanations

    tokens around underscores, especially double underscores, and also the words "in" and "as"

    oai_token-act-pair · gemini-2.0-flash

    _

    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
     itſelf
    -0.65
     vectorielles
    -0.65
     étoit
    -0.61
     feroit
    -0.60
     myſelf
    -0.59
    ειτουργ
    -0.58
    <bos>
    -0.58
     spéciaux
    -0.57
     Administrativna
    -0.57
    capace
    -0.57
    POSITIVE LOGITS
     []:
    0.97
    KommentareTeilen
    0.89
    ReusableCell
    0.89
    +#+#
    0.85
    abestanden
    0.82
    Slf
    0.79
     referrerpolicy
    0.77
    djangoproject
    0.76
    بوابة
    0.74
    __':
    0.73
    Activations Density 0.829%

    No Known Activations