© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7346
    Prev
    Next
    INDEX
    Explanations

    strings that are adjacent to a few very short tokens.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ences
    -0.41
    illes
    -0.41
    請繼續往下閱讀
    -0.39
     popolari
    -0.39
     alluminio
    -0.39
     esternos
    -0.39
    XXV
    -0.39
    val
    -0.39
    ue
    -0.38
    offsetWidth
    -0.38
    POSITIVE LOGITS
    ollectionView
    0.76
     CreateTagHelper
    0.73
    transQ
    0.70
    SequentialGroup
    0.69
     تضيفلها
    0.68
    stdc
    0.68
     BorderRadius
    0.68
    /**
    0.66
    openzeppelin
    0.64
    AxisAlignment
    0.62
    Activations Density 4.090%

    No Known Activations