© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4855
    Prev
    Next
    INDEX
    Explanations

    words related to eating

    oai_token-act-pair · gemini-2.0-flash

    Eating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     esternos
    -0.74
    \{\\
    -0.70
    PageModule
    -0.69
     nahilalakip
    -0.67
    SequentialGroup
    -0.65
    ]));
    -0.63
     NSCoder
    -0.63
    )}</
    -0.62
     препратки
    -0.60
    ]),
    -0.60
    POSITIVE LOGITS
     Featured
    0.47
     vi
    0.47
    Demografie
    0.46
    CharStream
    0.45
    Remove
    0.44
     Vogt
    0.43
    сель
    0.43
     Vi
    0.42
    ärin
    0.41
    velt
    0.41
    Activations Density 1.906%

    No Known Activations