© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5039
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, especially in French text

    oai_token-act-pair · gemini-2.0-flash

    me

    np_max-act · gemini-2.0-flash

    me

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     مشين
    -0.68
     externi
    -0.65
    withIdentifier
    -0.63
    ImageContext
    -0.61
    VIAF
    -0.60
    ArrowToggle
    -0.60
     Portail
    -0.57
     Devonian
    -0.56
    Portail
    -0.55
     étrangère
    -0.54
    POSITIVE LOGITS
     sich
    0.85
     Sich
    0.77
     się
    0.73
     zich
    0.72
     oneself
    0.66
    #+#
    0.65
    sich
    0.64
     الذات
    0.61
    ">—
    0.60
    mobileqq
    0.59
    Activations Density 0.424%

    No Known Activations