© 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. 3031
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and pronouns

    oai_token-act-pair · gemini-2.0-flash

    user-generated content

    np_max-act-logits · gemini-2.0-flash

    third-person pronoun

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ThroughAttribute
    -0.52
    例文帳に追加
    -0.47
    mphony
    -0.46
    Portail
    -0.46
    Neues
    -0.46
    featureID
    -0.45
    SerializedSize
    -0.42
    happens
    -0.42
     Picchu
    -0.42
     nobly
    -0.42
    POSITIVE LOGITS
    ChildScrollView
    0.74
     kasarigan
    0.67
    ReusableCell
    0.66
     resourceCulture
    0.63
    BeginContext
    0.61
    ŚĆ
    0.61
    UnusedPrivate
    0.59
    djangoproject
    0.58
    før
    0.57
     **)
    0.56
    Activations Density 16.989%

    No Known Activations