© 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. 10717
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and associated modal verbs like "can" and "want".

    oai_token-act-pair · gemini-2.0-flash

    can

    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
     henvisninger
    -0.66
    jsxFileName
    -0.63
    WriteTagHelper
    -0.59
    viewDidLoad
    -0.57
    endregion
    -0.57
    CloseOperation
    -0.57
    IBinder
    -0.56
    HandlerContext
    -0.54
    didSet
    -0.54
    complexType
    -0.53
    POSITIVE LOGITS
     noqa
    0.53
     怎样
    0.52
     sit
    0.51
     focus
    0.48
    舺
    0.48
     unavailable
    0.47
     whistle
    0.47
    шем
    0.46
    unable
    0.46
     verwalten
    0.45
    Activations Density 1.756%

    No Known Activations