© 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. 7195
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to affiliations and corruption

    oai_token-act-pair · gemini-2.0-flash

    connections/links/ties

    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
     Roskov
    -0.81
     Normdatei
    -0.79
    ItemBackground
    -0.73
    Geplaatst
    -0.62
    GOTREF
    -0.60
    
    -0.59
    randomUUID
    -0.57
    __":
    -0.56
    BASEPATH
    -0.53
    ulipas
    -0.52
    POSITIVE LOGITS
     connection
    2.14
     connections
    1.88
     Connection
    1.67
    connection
    1.64
     connect
    1.60
     connects
    1.58
     CONNECTION
    1.54
    Connection
    1.52
     ties
    1.52
     connecting
    1.52
    Activations Density 1.563%

    No Known Activations