© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8490
    Prev
    Next
    INDEX
    Explanations

    code snippets and the word tag/weight

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    abestanden
    -1.23
     myſelf
    -1.11
     itſelf
    -0.98
    enterOuterAlt
    -0.97
     Jefus
    -0.96
     ſeveral
    -0.96
     purpoſe
    -0.96
    تقاوى
    -0.94
    NUMX
    -0.91
    TagHelper
    -0.91
    POSITIVE LOGITS
     or
    0.59
    </strong>
    0.57
     
    0.54
     "
    0.50
     '
    0.49
    ,
    0.49
     sub
    0.47
     and
    0.47
     “
    0.47
    .
    0.46
    Activations Density 0.566%

    No Known Activations