© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4829
    Prev
    Next
    INDEX
    Explanations

    short, all-caps phrases describing the content on a website

    oai_token-act-pair · gemini-2.0-flash

    Website snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     the
    -0.57
     an
    -0.54
     me
    -0.48
     ir
    -0.43
     its
    -0.42
     a
    -0.41
     si
    -0.41
     Has
    -0.40
     Can
    -0.40
     it
    -0.40
    POSITIVE LOGITS
     Мексичка
    1.13
    RenderAtEndOf
    1.09
     US
    1.09
    IntoConstraints
    1.03
    Tikang
    1.02
     Biôgrafia
    0.98
     ويكيپيديا
    0.96
     snippetHide
    0.96
    EndGlobalSection
    0.94
     يتيمه
    0.94
    Activations Density 1.304%

    No Known Activations