© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9738
    Prev
    Next
    INDEX
    Explanations

    mentions of drug types and generations, likely when numbered

    oai_token-act-pair · gemini-2.0-flash

    generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     purpoſe
    -0.94
     houſe
    -0.87
     pleaſure
    -0.84
     ſtate
    -0.83
     EconPapers
    -0.83
     ſche
    -0.82
    MethodManager
    -0.81
     Efq
    -0.80
     Anſ
    -0.79
    :✨
    -0.79
    POSITIVE LOGITS
    <bos>
    1.08
    </b>
    0.94
    </i>
    0.91
    <b>
    0.84
    <i>
    0.82
    [toxicity=0]
    0.73
    '>
    0.70
    '
    0.68
    ’
    0.68
     intptr
    0.67
    Activations Density 33.891%

    No Known Activations