© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    computer hardware and software error reports

    oai_token-act-pair · gemini-2.0-flash

    Computer technical language

    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
     الدولى
    -0.45
     melu
    -0.43
     local
    -0.42
    รรม
    -0.41
     đồng
    -0.41
    LEncoder
    -0.41
    NEYS
    -0.41
    anggan
    -0.41
     IT
    -0.40
    osgi
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.94
    참고
    0.88
     itſelf
    0.87
    tvguidetime
    0.86
    IntoConstraints
    0.81
     متعلقه
    0.81
     Efq
    0.80
     myſelf
    0.78
     Audiodateien
    0.76
     himſelf
    0.74
    Activations Density 8.876%

    No Known Activations