© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    first person pronouns combined with modal verbs or 'to'

    oai_token-act-pair · gemini-2.0-flash

    First-person writing

    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
    Autoritní
    -0.75
     ComVisible
    -0.71
     trying
    -0.62
     preferring
    -0.62
    ever
    -0.61
    transQ
    -0.56
    لينكات
    -0.55
    HideFlags
    -0.55
     предпочита
    -0.53
     always
    -0.53
    POSITIVE LOGITS
     שוליים
    0.55
    tagHelperRunner
    0.52
    ArrowToggle
    0.51
    expandindo
    0.50
    횟
    0.48
    jarat
    0.47
     isComment
    0.47
    WAII
    0.43
    neem
    0.43
    moduleId
    0.42
    Activations Density 5.873%

    No Known Activations