© 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. 8415
    Prev
    Next
    INDEX
    Explanations

    mentions of officials in Edo State, Nigeria and their families

    oai_token-act-pair · gemini-2.0-flash

    including

    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
    FormTagHelper
    -0.75
     Monfieur
    -0.73
     IDisposable
    -0.71
     ſeveral
    -0.71
    出版年
    -0.70
     Theſe
    -0.70
    Sklici
    -0.67
    GraphicsUnit
    -0.66
     myſelf
    -0.66
     himſelf
    -0.65
    POSITIVE LOGITS
     am
    0.46
    orari
    0.43
     resourceCulture
    0.42
     peix
    0.39
    ip
    0.38
     im
    0.38
    皮
    0.38
    이의
    0.38
     N
    0.37
     dell
    0.36
    Activations Density 0.627%

    No Known Activations