© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4465
    Prev
    Next
    INDEX
    Explanations

    phrases describing customization to fit individual needs

    oai_token-act-pair · gemini-2.0-flash

    tailoring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     une
    -0.56
    ↵↵
    -0.51
     (
    -0.48
     
    -0.48
     ter
    -0.48
     Ad
    -0.48
     vy
    -0.47
     |
    -0.47
     vo
    -0.47
    照
    -0.47
    POSITIVE LOGITS
     Roskov
    1.18
    +#+#
    0.95
    Personensuche
    0.95
    QMetaType
    0.87
     Italijani
    0.84
     nahilalakip
    0.84
    ArrowToggle
    0.84
    Vidite
    0.83
     Obrador
    0.82
    XmlAccessorType
    0.81
    Activations Density 2.890%

    No Known Activations