© 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. 695
    Prev
    Next
    INDEX
    Explanations

    words that describe the state or quality of something, particularly its condition, deficiencies over time, and steps needed to address those deficiencies.

    oai_token-act-pair · gemini-2.0-flash

    condition

    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
    WebElementEntity
    -0.61
    RegressionTest
    -0.60
    enumi
    -0.58
    rawDesc
    -0.57
     useRouter
    -0.57
    TagHelper
    -0.56
    PreferredItem
    -0.54
    ;">
    -0.53
    RenderAtEndOf
    -0.53
    URLException
    -0.52
    POSITIVE LOGITS
     condition
    2.73
     Condition
    2.36
    condition
    2.31
     CONDITION
    2.14
    Condition
    2.06
    CONDITION
    1.75
     condición
    1.69
     condição
    1.60
     condizione
    1.59
     condi
    1.36
    Activations Density 2.766%

    No Known Activations