© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and adjectives, especially in the possessive form

    oai_token-act-pair · gemini-2.0-flash

    words related to personal experiences and memories

    np_token-act-pair-logits · gpt-4o-mini

    experiences/feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DockStyle
    -0.90
    TagMode
    -0.87
    AccessorTable
    -0.80
    elemField
    -0.78
    InjectAttribute
    -0.75
     AssemblyCulture
    -0.74
    AndEndTag
    -0.71
    PerformLayout
    -0.70
    脚注の使い方
    -0.65
    цездатний
    -0.64
    POSITIVE LOGITS
    
    0.61
     experiences
    0.61
     frustrations
    0.57
     escap
    0.55
     preferences
    0.54
     sür
    0.53
     desires
    0.53
     adventures
    0.52
    habit
    0.51
     habit
    0.50
    Activations Density 1.927%

    No Known Activations