© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 670
    Prev
    Next
    INDEX
    Explanations

    the word "this", along with some words and phrases that are sometimes associated with "this".

    oai_token-act-pair · gemini-2.0-flash

    This

    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
    PerformLayout
    -0.83
    ]";
    -0.66
    ).</
    -0.66
    .)}
    -0.65
    '";
    -0.63
    $}}
    -0.62
    '");
    -0.60
    )";
    -0.60
    )";
    
    -0.60
     AssemblyTitle
    -0.59
    POSITIVE LOGITS
    uxxxx
    0.64
     Sorbonne
    0.60
     botanist
    0.59
     eorum
    0.59
     Bélgica
    0.58
     direto
    0.57
     USN
    0.55
     unseen
    0.54
     sırt
    0.54
     Italie
    0.54
    Activations Density 2.908%

    No Known Activations