© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4163
    Prev
    Next
    INDEX
    Explanations

    instances of the contraction "I'd" (I would/I had) and the phrase "would like"

    oai_token-act-pair · gemini-2.0-flash

    "I'd/would like"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    jorde
    -0.59
    ".$_
    -0.58
     Gurney
    -0.56
     Concern
    -0.54
    iburg
    -0.53
    inafter
    -0.52
    ^(@)
    -0.51
    eroll
    -0.50
     Sink
    -0.50
    nalpot
    -0.49
    POSITIVE LOGITS
     rather
    0.65
    ImageContext
    0.63
    fjspx
    0.59
     Rather
    0.59
    GenerationType
    0.59
     plutôt
    0.56
    Rather
    0.56
    rénées
    0.54
     estekak
    0.54
    rather
    0.53
    Activations Density 0.815%

    No Known Activations