© 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. 14090
    Prev
    Next
    INDEX
    Explanations

    various popular phrases, legal jargon, technology terms and religious terminology

    oai_token-act-pair · gemini-2.0-flash

    STEM

    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
     NUKAT
    -1.16
     Italijanski
    -1.09
     himo
    -1.07
    sizeCache
    -1.06
    oredCriteria
    -1.05
    تقاوى
    -1.04
    Personensuche
    -1.01
    ConstraintMaker
    -0.96
    цездатний
    -0.95
     myſelf
    -0.94
    POSITIVE LOGITS
     [
    0.47
    -
    0.44
     and
    0.44
     at
    0.41
    <eos>
    0.40
     originally
    0.40
     among
    0.38
     (
    0.38
    一样
    0.37
     even
    0.36
    Activations Density 0.400%

    No Known Activations