© 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. 14667
    Prev
    Next
    INDEX
    Explanations

    mentions of gas, especially natural gas or toxic gas

    oai_token-act-pair · gemini-2.0-flash

    gas and explosions

    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
     gas
    -2.61
     Gas
    -2.56
    Gas
    -2.50
     GAS
    -2.28
    gas
    -2.25
    GAS
    -2.16
     gases
    -1.73
     газо
    -1.62
     gaseous
    -1.59
    ガス
    -1.51
    POSITIVE LOGITS
    }());
    0.52
     AppCompatTheme
    0.49
    ộm
    0.47
     فريبيس
    0.47
    ContentLoaded
    0.46
     plaît
    0.45
    ellón
    0.45
     orto
    0.45
     Alma
    0.44
    roidered
    0.43
    Activations Density 1.657%

    No Known Activations