© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12070
    Prev
    Next
    INDEX
    Explanations

    the word "who"

    oai_token-act-pair · gemini-2.0-flash

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.11
     defaultstate
    -0.93
    sizeCache
    -0.77
    StreetMap
    -0.75
     CreateTagHelper
    -0.72
    awtextra
    -0.71
    msgTypes
    -0.70
     تانيه
    -0.68
    IBOutlet
    -0.66
    #
    -0.66
    POSITIVE LOGITS
     behaviour
    0.46
    toBe
    0.45
     algun
    0.45
     знает
    0.44
    rind
    0.44
    ximity
    0.43
     Winning
    0.43
    Winning
    0.42
    Knows
    0.42
     hers
    0.42
    Activations Density 0.464%

    No Known Activations