© 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. 8555
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to software, apps, and content creation

    oai_token-act-pair · gemini-2.0-flash

    software and apps

    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
    sizeCache
    -0.49
     nevo
    -0.44
    tableFuture
    -0.44
     Hush
    -0.43
     Azad
    -0.42
    Portail
    -0.42
     ujedno
    -0.42
    حياتها
    -0.41
     Karo
    -0.41
     endforeach
    -0.41
    POSITIVE LOGITS
    mybatisplus
    0.69
     esternos
    0.68
     تضيفلها
    0.58
     ویکی‌پدیای
    0.55
    èdia
    0.53
    Референце
    0.52
     Administrativna
    0.52
     MenuView
    0.51
     snippetHide
    0.51
    енча
    0.50
    Activations Density 7.179%

    No Known Activations