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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4483
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns combined with thoughts and feelings

    oai_token-act-pair · gemini-2.0-flash

    Referencing a female character

    np_max-act-logits · gemini-2.0-flash
    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
     She
    -0.92
     them
    -0.86
    She
    -0.85
     ň
    -0.82
    LookAnd
    -0.74
     quale
    -0.71
     useState
    -0.69
    them
    -0.69
    initComponents
    -0.69
    useState
    -0.68
    POSITIVE LOGITS
     her
    2.55
    her
    1.68
    Her
    1.40
     ihr
    1.38
     HER
    1.19
     Her
    1.12
     haar
    1.05
    HER
    0.96
    她的
    0.93
     Ihr
    0.83
    Activations Density 7.399%

    No Known Activations