© 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. 869
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers, letters, and characters

    oai_token-act-pair · gemini-2.0-flash

    source code diffs

    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
    出版年
    -0.97
    </code>
    -0.84
    </td>
    -0.84
    </s>
    -0.82
     
    -0.82
     […]
    -0.81
    ",
    -0.80
    </h3>
    -0.78
    </h4>
    -0.77
    </h2>
    -0.77
    POSITIVE LOGITS
    ↵↵
    1.78
    ↵
    1.76
    ↵↵↵
    1.33
    ↵↵↵↵
    1.27
    ↵↵↵↵↵
    1.13
    ↵↵↵↵↵↵
    1.09
    ↵↵↵↵↵↵↵
    1.02
    ↵↵↵↵↵↵↵↵
    1.01
    ↵↵↵↵↵↵↵↵↵↵
    0.87
    ↵↵↵↵↵↵↵↵↵
    0.84
    Activations Density 3.726%

    No Known Activations