© 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. 15157
    Prev
    Next
    INDEX
    Explanations

    words related to marijuana legislation

    oai_token-act-pair · gemini-2.0-flash

    legal

    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
    MemoryWarning
    -0.91
     متعلقه
    -0.59
     vulgaires
    -0.56
     HttpStatusCode
    -0.52
     hObject
    -0.52
    RegistryLite
    -0.51
     cures
    -0.51
     kaarangay
    -0.50
    MessageOf
    -0.49
     виправивши
    -0.49
    POSITIVE LOGITS
     legal
    2.25
    legal
    1.97
     Legal
    1.96
    Legal
    1.91
     LEGAL
    1.80
    LEGAL
    1.50
     legales
    1.39
     legale
    1.35
     legais
    1.16
     légal
    1.13
    Activations Density 4.625%

    No Known Activations