© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 804
    Prev
    Next
    INDEX
    Explanations

    words related to auditing and financial regulation

    oai_token-act-pair · gemini-2.0-flash

    Finance news

    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
    ContentAsync
    -0.87
     Reſ
    -0.84
    ſelf
    -0.81
     pleaſure
    -0.80
     raiſ
    -0.78
    ThroughAttribute
    -0.77
     purpoſe
    -0.73
     transférez
    -0.73
     quæ
    -0.73
     themſelves
    -0.73
    POSITIVE LOGITS
     Nat
    0.47
    Personendaten
    0.42
    PreferredItem
    0.40
    Nat
    0.39
     Ent
    0.37
    embley
    0.36
     Vargas
    0.35
     Pal
    0.35
    immune
    0.35
    Twig
    0.34
    Activations Density 3.180%

    No Known Activations