© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15207
    Prev
    Next
    INDEX
    Explanations

    mentions of specific ingredients and the cultivation, preparation, and health aspects of cannabis and food.

    oai_token-act-pair · gemini-2.0-flash

    Random sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UIControlState
    -0.61
    othed
    -0.54
     précédents
    -0.50
     glassy
    -0.49
     connessione
    -0.48
     découver
    -0.47
    니
    -0.47
     précédentes
    -0.47
     transfieras
    -0.47
    jš
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.68
     مشين
    0.65
    .*")]
    0.59
    urlpatterns
    0.59
    addCriterion
    0.58
     GenerationType
    0.57
     Auto
    0.54
    __':
    0.53
     محفوظة
    0.52
     auto
    0.51
    Activations Density 0.933%

    No Known Activations