© 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. 16011
    Prev
    Next
    INDEX
    Explanations

    the context of personal names, especially in legal or narrative settings

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    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
     getItemId
    -0.65
    devamını
    -0.50
    anyuan
    -0.50
    Personendaten
    -0.50
     MenuView
    -0.48
    AllowUser
    -0.46
     برانيه
    -0.46
    miary
    -0.45
    ClientSize
    -0.45
     Iyer
    -0.44
    POSITIVE LOGITS
    PickerController
    0.83
     Hicks
    0.73
     Flick
    0.73
     Hick
    0.73
    ruck
    0.71
    racked
    0.70
     Frick
    0.69
     Puck
    0.68
    hack
    0.68
     Peck
    0.68
    Activations Density 4.041%

    No Known Activations