© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4781
    Prev
    Next
    INDEX
    Explanations

    abbreviations and surnames

    oai_token-act-pair · gemini-2.0-flash

    Technical or geographical context

    np_max-act-logits · 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
    protoimpl
    -0.89
    UrlResolution
    -0.79
    RunAsync
    -0.79
    CppMethod
    -0.78
     resourceCulture
    -0.75
    Personendaten
    -0.74
     HasFactory
    -0.72
    sizeCache
    -0.72
     >=",
    -0.71
    oprot
    -0.71
    POSITIVE LOGITS
    ↵↵
    0.61
     تانيه
    0.40
    Vidite
    0.36
    <eos>
    0.35
     referenties
    0.35
    iltà
    0.28
     Single
    0.27
     One
    0.25
    为止
    0.25
    余談
    0.24
    Activations Density 0.138%

    No Known Activations