© 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. 2381
    Prev
    Next
    INDEX
    Explanations

    first-person references to family members or personal possessions.

    oai_token-act-pair · gemini-2.0-flash

    my

    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
     my
    -1.02
     My
    -0.85
    My
    -0.85
     miei
    -0.77
     MY
    -0.75
     myſelf
    -0.71
    Моя
    -0.70
    my
    -0.68
     Theſe
    -0.68
     Meu
    -0.67
    POSITIVE LOGITS
    reg
    0.49
    par
    0.47
    AccessType
    0.44
    ir
    0.43
    pat
    0.42
    διά
    0.42
    ote
    0.41
    گرام
    0.41
    indépendance
    0.40
    ய
    0.40
    Activations Density 1.591%

    No Known Activations