© 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. 3298
    Prev
    Next
    INDEX
    Explanations

    words related to US legislative bodies with a focus on political parties

    oai_token-act-pair · gemini-2.0-flash

    House or Senate

    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
    setVerticalGroup
    -1.07
    脚注の使い方
    -1.04
    rungsseite
    -1.02
    Personendaten
    -1.01
     defaultstate
    -1.00
     AssemblyCulture
    -0.99
    styleType
    -0.96
     snippetHide
    -0.95
    Hentet
    -0.95
    posedge
    -0.91
    POSITIVE LOGITS
    G
    0.40
    前
    0.37
    엑
    0.33
    ci
    0.33
     g
    0.33
    下
    0.32
     dingin
    0.32
     claves
    0.31
     Government
    0.31
     Action
    0.31
    Activations Density 1.950%

    No Known Activations