© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5594
    Prev
    Next
    INDEX
    Explanations

    words related to analysis or reporting that may appear in legal or scientific settings

    oai_token-act-pair · gemini-2.0-flash

    Giving context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     informée
    -0.76
     autorytatywna
    -0.71
    <bos>
    -0.68
    apimachinery
    -0.68
     utafitiHapana
    -0.67
    GEBURTSDATUM
    -0.65
    efeller
    -0.61
    Personendaten
    -0.60
    BufferException
    -0.56
    imetsu
    -0.54
    POSITIVE LOGITS
    principalColumn
    0.60
    íté
    0.51
     neutral
    0.49
    ullar
    0.48
    >//
    0.48
    lyst
    0.48
    yki
    0.48
    InputBorder
    0.47
     Begle
    0.47
    colta
    0.46
    Activations Density 24.247%

    No Known Activations