© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 815
    Prev
    Next
    INDEX
    Explanations

    words related to writing papers, articles, and podcasts, and words related to discussing or explaining things.

    oai_token-act-pair · gemini-2.0-flash

    discussion

    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
     LayoutInflater
    -0.54
     chịu
    -0.54
    Hochspringen
    -0.54
    렇
    -0.53
    ecap
    -0.52
     SafeMath
    -0.52
    GOTREF
    -0.51
    IntoConstraints
    -0.50
     uns
    -0.50
     intéress
    -0.50
    POSITIVE LOGITS
    <bos>
    1.41
    bitat
    0.52
     NavController
    0.50
    quité
    0.50
    djangoproject
    0.50
     ModelExpression
    0.49
     fufficient
    0.48
     Esau
    0.47
    therin
    0.47
     Barcelone
    0.46
    Activations Density 1.953%

    No Known Activations