© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10410
    Prev
    Next
    INDEX
    Explanations

    the fragment "ma" in the middle of a word

    oai_token-act-pair · gemini-2.0-flash

    Code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    FieldDescriptor
    -0.50
    parseLong
    -0.42
    rawDesc
    -0.42
     distanciation
    -0.41
     جغرافيا
    -0.39
     case
    -0.39
     herman
    -0.38
    ditto
    -0.38
     benne
    -0.38
    INCREMENT
    -0.37
    POSITIVE LOGITS
     BoxFit
    0.96
     NSCoder
    0.67
    IntoConstraints
    0.65
     isChecked
    0.64
    enderror
    0.62
     BoxDecoration
    0.60
    }}]{
    0.59
    /*
    0.58
     manquer
    0.58
    存于互联网档案馆
    0.57
    Activations Density 0.207%

    No Known Activations