© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12394
    Prev
    Next
    INDEX
    Explanations

    the phrase "This API requires the following"

    oai_token-act-pair · gemini-2.0-flash

    code and APIs

    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
     للمعارف
    -0.76
     تانيه
    -0.73
     AssemblyCompany
    -0.71
    writeField
    -0.69
    يكب
    -0.65
    enderror
    -0.65
    DockStyle
    -0.65
     beginnetje
    -0.61
    complexContent
    -0.61
     ]
    -0.61
    POSITIVE LOGITS
    //
    0.46
    mi
    0.44
     muz
    0.41
    AlterField
    0.40
    cua
    0.39
     LoggerFactory
    0.39
     medis
    0.38
     hore
    0.38
    didSet
    0.38
    wpi
    0.37
    Activations Density 0.271%

    No Known Activations