© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12089
    Prev
    Next
    INDEX
    Explanations

    code with square brackets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    vieja
    -0.47
     as
    -0.47
     Schell
    -0.43
     cứng
    -0.43
     überzeugt
    -0.43
    wesenheit
    -0.42
     capilla
    -0.41
    vár
    -0.41
    ergic
    -0.41
    krivning
    -0.41
    POSITIVE LOGITS
    ]--;
    1.04
    ,:);
    0.91
    NameInMap
    0.91
    __':
    0.88
    ReusableCell
    0.84
    __':
    0.82
    MENAFN
    0.82
    ,:),
    0.81
    __":
    0.81
    --){
    0.79
    Activations Density 12.107%

    No Known Activations