© 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. 842
    Prev
    Next
    INDEX
    Explanations

    sections of dialog in a transcript

    oai_token-act-pair · gemini-2.0-flash

    Formal speech and royalty

    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
    Sir
    -1.93
     Sir
    -1.90
     Lord
    -1.77
     Lady
    -1.76
    Lord
    -1.68
    Lady
    -1.64
     sir
    -1.63
     lord
    -1.63
     LADY
    -1.59
    SIR
    -1.58
    POSITIVE LOGITS
    XMLSchema
    0.70
    Geplaatst
    0.62
     архивлан
    0.60
     tartalomajánló
    0.55
    GraphicsUnit
    0.55
    enumi
    0.53
    uscular
    0.53
    InputTagHelper
    0.52
    ябре
    0.51
    ביוגרפיה
    0.50
    Activations Density 1.965%

    No Known Activations