© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5262
    Prev
    Next
    INDEX
    Explanations

    section headings of varying formats

    oai_token-act-pair · gemini-2.0-flash

    archaic or formal texts

    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
     v
    -0.72
     p
    -0.66
    :✨
    -0.65
      (
    -0.63
     n
    -0.63
     P
    -0.61
     y
    -0.59
     C
    -0.58
     is
    -0.57
     Sa
    -0.57
    POSITIVE LOGITS
     itſelf
    1.43
     myſelf
    1.16
     ſtate
    1.13
     Reſ
    1.09
     Houſe
    1.08
     unſ
    1.08
     purpoſe
    1.08
     Diſ
    1.07
     pleaſure
    1.07
    ſelves
    1.06
    Activations Density 4.410%

    No Known Activations