© 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. 3420
    Prev
    Next
    INDEX
    Explanations

    words related to connecting different places or things

    oai_token-act-pair · gemini-2.0-flash

    connect

    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
     connection
    -2.41
     connect
    -2.20
     connections
    -2.09
    connection
    -2.08
     Connection
    -2.06
     connecting
    -2.05
     connects
    -1.98
     connected
    -1.96
    connect
    -1.96
    Connection
    -1.92
    POSITIVE LOGITS
    ⓧ
    0.82
     оригіналу
    0.74
    NewUrlParser
    0.72
    "],
    0.71
    )"),
    0.71
     MainAxisSize
    0.70
    UTERS
    0.69
    "])
    0.68
    __(/*!
    0.67
    }")
    0.66
    Activations Density 5.398%

    No Known Activations