© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4343
    Prev
    Next
    INDEX
    Explanations

    words related to meanings or to things being at risk

    oai_token-act-pair · gemini-2.0-flash

    mean stake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     démoc
    -0.61
     "..\..\
    -0.56
    leun
    -0.54
     bellow
    -0.51
    mbers
    -0.50
     Reina
    -0.50
    ✨:
    -0.50
     terciopelo
    -0.49
    roo
    -0.49
     Mantle
    -0.48
    POSITIVE LOGITS
    IsMutable
    0.73
     Вікі
    0.68
    detectChanges
    0.67
    OGND
    0.64
     ModelExpression
    0.62
    ValueStyle
    0.60
    וויק
    0.60
    awtextra
    0.58
     ProtoMessage
    0.57
     Référence
    0.54
    Activations Density 2.736%

    No Known Activations