© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16230
    Prev
    Next
    INDEX
    Explanations

    terms related to finance and economics

    oai_token-act-pair · gemini-2.0-flash

    financial

    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
    httphttps
    -0.74
     {}'.
    -0.71
    AlterField
    -0.70
    WithIOException
    -0.68
     InputDecoration
    -0.68
    fillType
    -0.68
     AssemblyCompany
    -0.66
    '},
    -0.65
     jspb
    -0.65
    "]/
    -0.65
    POSITIVE LOGITS
    ミス
    0.36
    ir
    0.36
    sejarah
    0.35
    Біографія
    0.35
     Y
    0.33
     well
    0.33
     vál
    0.32
    र्फ
    0.32
    ast
    0.32
     oils
    0.32
    Activations Density 1.220%

    No Known Activations