© 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. 14848
    Prev
    Next
    INDEX
    Explanations

    words that describe or define a person's direction in their existence

    oai_token-act-pair · gemini-2.0-flash

    personal

    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
    Datuak
    -0.60
    develop
    -0.57
    OptionsMenu
    -0.57
    Development
    -0.56
    Growth
    -0.55
     Develop
    -0.55
     Development
    -0.54
     SwitchCompat
    -0.53
     utveck
    -0.53
    growth
    -0.52
    POSITIVE LOGITS
     personal
    0.79
     initComponents
    0.75
     Personal
    0.75
    Personal
    0.73
    personal
    0.68
     PERSONAL
    0.65
     HasFactory
    0.64
    PERSONAL
    0.60
     pessoal
    0.60
    sizeCache
    0.59
    Activations Density 1.629%

    No Known Activations