© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4533
    Prev
    Next
    INDEX
    Explanations

    various keywords found in programming languages and code

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    __":
    -0.96
    ")));
    -0.86
    Datuak
    -0.84
    __':
    -0.82
     nahilalakip
    -0.77
    )));
    -0.70
    enumii
    -0.70
    __":
    -0.70
    '));
    -0.70
    "}},
    -0.70
    POSITIVE LOGITS
    ItemBackground
    0.50
     block
    0.48
    ValueStyle
    0.46
    équences
    0.44
    銘
    0.42
    ThemeOverlay
    0.42
    spesies
    0.41
     classico
    0.41
    tituto
    0.40
     bribes
    0.40
    Activations Density 2.530%

    No Known Activations