© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1152
    Prev
    Next
    INDEX
    Explanations

    phrases used in financial news reports

    oai_token-act-pair · gemini-2.0-flash

    economics and policy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AssemblyTitle
    -0.69
     AssemblyCulture
    -0.69
    Portale
    -0.66
     SafeMath
    -0.63
     الحره
    -0.62
    istoitu
    -0.61
    MessageTagHelper
    -0.60
     uku
    -0.60
    DECREF
    -0.59
    omla
    -0.57
    POSITIVE LOGITS
    |}{}
    0.45
    ్రామ
    0.45
     bezeichneter
    0.43
    Siehe
    0.43
     ffilmiau
    0.42
    jsdelivr
    0.41
    <>("
    0.41
    brigens
    0.40
     './../
    0.40
     Liber
    0.40
    Activations Density 9.479%

    No Known Activations