© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8820
    Prev
    Next
    INDEX
    Explanations

    instances of abstract nouns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     reasons
    -0.68
     ways
    -0.68
     pleasures
    -0.67
     dangers
    -0.67
     realities
    -0.66
    fahrens
    -0.64
     يتيمه
    -0.64
    Personensuche
    -0.64
     effects
    -0.63
    attempts
    -0.63
    POSITIVE LOGITS
    tagext
    0.46
    texttt
    0.45
    
    0.45
    abestanden
    0.43
    atier
    0.42
    enschappelijke
    0.40
    ⎪
    0.38
    serviceWorker
    0.37
    FXML
    0.37
    tôi
    0.37
    Activations Density 37.761%

    No Known Activations