© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9457
    Prev
    Next
    INDEX
    Explanations

    words related to monetary payment, error messages and code

    oai_token-act-pair · gemini-2.0-flash

    charges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     is
    -0.50
     per
    -0.49
     can
    -0.48
     he
    -0.47
     system
    -0.45
     se
    -0.45
     sau
    -0.45
     mari
    -0.45
     
    -0.45
     in
    -0.44
    POSITIVE LOGITS
     Normdatei
    1.09
     CreateTagHelper
    1.06
    原始内容存档于
    1.05
     myſelf
    1.04
    VIAF
    1.04
     disambiguazione
    1.04
    ValueStyle
    1.01
     itſelf
    1.00
     يتيمه
    0.99
    IntoConstraints
    0.99
    Activations Density 2.332%

    No Known Activations