© 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. 11418
    Prev
    Next
    INDEX
    Explanations

    scientific writing about plant-based chemistry discussing particular elements and compounds

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds

    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
    SBATCH
    -0.71
    Rhestr
    -0.69
    OGND
    -0.60
     engraçadas
    -0.59
     bezeichneter
    -0.58
    strix
    -0.58
     فريبيس
    -0.57
     cherchés
    -0.57
    WebMethod
    -0.57
    providedIn
    -0.57
    POSITIVE LOGITS
     asfal
    0.48
    ेर
    0.46
     croc
    0.45
    ագրություններ
    0.45
     catar
    0.44
    unno
    0.44
    CardContent
    0.43
     cr
    0.42
     coar
    0.41
     urs
    0.41
    Activations Density 8.497%

    No Known Activations