© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13974
    Prev
    Next
    INDEX
    Explanations

    words related to answering a question like `can`, `fine`,`strange`, `is`, `if`, and `thing`

    oai_token-act-pair · gemini-2.0-flash

    Code troubleshooting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    bitField
    -0.59
    <bos>
    -0.54
     незавершена
    -0.50
     triplets
    -0.48
    XmlIgnore
    -0.47
    Blurb
    -0.47
     useAppContext
    -0.46
    AutoScale
    -0.45
    Rujuakan
    -0.45
    clo
    -0.44
    POSITIVE LOGITS
    AnimationsModule
    0.68
    __);
    0.58
    orla
    0.56
    XtraReports
    0.56
     utafitiHapana
    0.56
    BagLayout
    0.51
     BoxFit
    0.51
     contenus
    0.50
    הערות
    0.50
    المناصب
    0.49
    Activations Density 0.435%

    No Known Activations