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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14376
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially SQL queries and related terms like 'alpha' and 'partial'.

    oai_token-act-pair · gemini-2.0-flash

    sql

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AndEndTag
    -1.15
     purpoſe
    -1.13
     démocr
    -1.09
     pleaſure
    -1.08
    ValueStyle
    -1.07
     giustizia
    -1.07
     fédé
    -1.03
     quæ
    -1.01
     chrétien
    -1.01
     ویکی‌پدیای
    -0.98
    POSITIVE LOGITS
     
    0.87
    ↵↵
    0.84
    </em>
    0.68
    ور
    0.63
    s
    0.63
    The
    0.62
     The
    0.60
     '
    0.59
    <em>
    0.58
     tam
    0.58
    Activations Density 1.945%

    No Known Activations