© 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. 14637
    Prev
    Next
    INDEX
    Explanations

    the word "practical" and words that are semantically related to it.

    oai_token-act-pair · gemini-2.0-flash

    practical

    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
    CodedInputStream
    -0.60
    EDEFAULT
    -0.53
    uspiel
    -0.52
    ).]
    -0.52
    tanleria
    -0.52
     Otherwise
    -0.50
    Enders
    -0.49
    PreferredItem
    -0.49
    subsubsection
    -0.49
     convi
    -0.48
    POSITIVE LOGITS
     abstrait
    0.96
     feroit
    0.95
     debout
    0.86
     devenus
    0.84
     officiellement
    0.84
    <bos>
    0.82
     pitié
    0.81
     incroy
    0.81
     vertes
    0.81
     ainfi
    0.78
    Activations Density 2.090%

    No Known Activations