© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10532
    Prev
    Next
    INDEX
    Explanations

    acronyms of government agencies and organizations, especially those related to science and the environment

    oai_token-act-pair · gemini-2.0-flash

    government agencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     saites
    -0.56
    tagHelperRunner
    -0.56
     }^{[
    -0.51
     '**
    -0.50
    saraba
    -0.50
    Gön
    -0.49
    Controllo
    -0.49
    いかがでしょうか
    -0.47
    లాలు
    -0.46
     sibi
    -0.45
    POSITIVE LOGITS
     InputDecoration
    0.66
    styleType
    0.63
    COUN
    0.59
     beginnetje
    0.56
    tvguidetime
    0.53
     Early
    0.52
    releasing
    0.52
     ujednoznacz
    0.52
    mbggenerated
    0.51
    mybatisplus
    0.51
    Activations Density 1.482%

    No Known Activations