© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    words and entities related to businesses and brands, and potentially some internet slang/online abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Lite

    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
     يتيمه
    -0.84
    ніципалі
    -0.79
     Chwiliwch
    -0.77
    ConstraintMaker
    -0.70
    titleMargin
    -0.69
    LabelTagHelper
    -0.69
    fjspx
    -0.66
    AndroidJUnit
    -0.66
    PerformLayout
    -0.64
    تفصیلات
    -0.64
    POSITIVE LOGITS
    .
    0.45
    dom
    0.40
    ess
    0.40
     Dad
    0.40
     Well
    0.38
     And
    0.38
    ment
    0.38
     Arkivert
    0.38
     I
    0.38
    ou
    0.38
    Activations Density 4.855%

    No Known Activations