© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10944
    Prev
    Next
    INDEX
    Explanations

    the word 'when' and related words 'was', 'were'

    oai_token-act-pair · gemini-2.0-flash

    When

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    altham
    -0.44
     hauts
    -0.43
    Once
    -0.43
     parcela
    -0.40
    once
    -0.39
    Scher
    -0.39
     chaqueta
    -0.39
     Once
    -0.39
     när
    -0.38
     jouets
    -0.38
    POSITIVE LOGITS
    GOTREF
    1.04
    MemoryWarning
    1.03
    Personensuche
    1.02
    DockStyle
    0.96
    MessageOf
    0.89
    ChildScrollView
    0.87
     ModelExpression
    0.86
    WriteBarrier
    0.86
     дописавши
    0.84
    XmlAccessType
    0.82
    Activations Density 2.916%

    No Known Activations