© 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. 3340
    Prev
    Next
    INDEX
    Explanations

    mentions of legal entities, government organizations and hospital emergency rooms

    oai_token-act-pair · gemini-2.0-flash

    County

    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
    出版年
    -0.84
    ſelf
    -0.84
    ſelves
    -0.78
     Majefty
    -0.78
     doubtnut
    -0.77
    öglichkeiten
    -0.77
     Jefus
    -0.76
    __':
    -0.75
     مرئيه
    -0.75
    %"),
    -0.74
    POSITIVE LOGITS
     referenties
    0.46
     contamos
    0.42
     Púb
    0.40
     federal
    0.39
     thị
    0.38
    Palmar
    0.37
     esternos
    0.36
    ドライ
    0.36
    WithMany
    0.35
     completa
    0.35
    Activations Density 1.908%

    No Known Activations