© 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. 818
    Prev
    Next
    INDEX
    Explanations

    persuasive language in various types of text

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    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
     Athenians
    -0.54
     TTS
    -0.47
     Esau
    -0.45
    adecimal
    -0.44
     Florentine
    -0.44
     Mongols
    -0.43
     Caspian
    -0.43
     Legendre
    -0.43
     EEU
    -0.42
     Brutus
    -0.41
    POSITIVE LOGITS
     Confidence
    0.92
     Practical
    0.92
     Positive
    0.91
     Expensive
    0.91
     Proper
    0.91
     Safe
    0.90
     Comfort
    0.89
     Critical
    0.89
     Difficult
    0.89
     Serious
    0.89
    Activations Density 22.151%

    No Known Activations