© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15186
    Prev
    Next
    INDEX
    Explanations

    acronyms that are spelled out elsewhere in the document

    oai_token-act-pair · gemini-2.0-flash

    FA

    np_max-act-logits · gemini-2.0-flash

    say ")"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ModelExpression
    -0.87
    AndEndTag
    -0.74
     Signalez
    -0.73
     intptr
    -0.73
    photobucket
    -0.70
     onAnimation
    -0.69
    脚注の使い方
    -0.68
    хьтан
    -0.67
    FunctionFlags
    -0.66
    ########.
    -0.66
    POSITIVE LOGITS
    </strong>
    0.65
    )
    0.56
    </
    0.51
    </em>
    0.50
    </code>
    0.47
    }
    0.43
    ),
    0.41
    </blockquote>
    0.41
     Logement
    0.40
    "
    0.40
    Activations Density 2.578%

    No Known Activations