© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14189
    Prev
    Next
    INDEX
    Explanations

    phrases related to excess, lateness or sickness

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     MainAxisSize
    -0.85
    RetentionPolicy
    -0.79
     BoxDecoration
    -0.75
     createSlice
    -0.74
    parsedMessage
    -0.73
     فريبيس
    -0.72
    }{*}{}
    -0.71
    ModelForm
    -0.71
     оригіналу
    -0.71
    Personensuche
    -0.69
    POSITIVE LOGITS
     too
    1.23
    Too
    1.15
     Too
    1.13
    too
    1.06
     TOO
    1.02
    TOO
    0.88
     demasi
    0.84
     слишком
    0.83
     zbyt
    0.75
     demasiado
    0.72
    Activations Density 0.271%

    No Known Activations