© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14467
    Prev
    Next
    INDEX
    Explanations

    the phrase "in advance".

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    Negative Logits
    ^(@)
    -1.16
     Efq
    -1.09
    RenderAtEndOf
    -1.05
     дописавши
    -1.02
     EconPapers
    -1.01
    WebVitals
    -0.98
     ProtoMessage
    -0.93
    ruptedException
    -0.92
    MLLoader
    -0.92
    NUMX
    -0.91
    POSITIVE LOGITS
    -
    0.52
    get
    0.46
    to
    0.46
    go
    0.44
    ut
    0.43
    at
    0.42
    the
    0.42
    ga
    0.41
    v
    0.41
    gan
    0.40
    Activations Density 2.034%

    No Known Activations