© 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. 10511
    Prev
    Next
    INDEX
    Explanations

    forms of the auxiliary verb "do"

    oai_token-act-pair · gemini-2.0-flash

    did

    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
     soient
    -0.84
    Be
    -0.82
     aient
    -0.77
     InputDecoration
    -0.77
     be
    -0.77
     puissent
    -0.75
     siano
    -0.68
    be
    -0.66
     possano
    -0.63
     Be
    -0.62
    POSITIVE LOGITS
     acquire
    0.83
     speak
    0.82
     send
    0.82
     detect
    0.78
     convert
    0.77
     translate
    0.77
     marry
    0.77
     purchase
    0.76
     get
    0.75
     install
    0.75
    Activations Density 4.060%

    No Known Activations