© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11487
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    words related to television

    np_token-act-pair-logits · gpt-4o-mini

    television, TV

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Legit
    -0.57
    openzeppelin
    -0.56
     Procurement
    -0.56
     endwhile
    -0.55
    ParallelGroup
    -0.53
     <>",
    -0.53
     procurement
    -0.52
    BeginContext
    -0.51
     للبيع
    -0.51
    odiment
    -0.51
    POSITIVE LOGITS
     TV
    1.02
     television
    0.90
     tv
    0.89
    TV
    0.85
     DVD
    0.82
     Television
    0.77
     microwave
    0.77
     televisions
    0.75
     Tv
    0.74
     televis
    0.71
    Activations Density 1.695%

    No Known Activations