© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6171
    Prev
    Next
    INDEX
    Explanations

    figure captions for multi-panel plots that discuss "top", "bottom", "left", and "right" panels, "dashed lines", and/or spline mathematics

    oai_token-act-pair · gemini-2.0-flash

    Figures and panels

    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
     left
    -1.68
     LEFT
    -1.46
     Left
    -1.46
     right
    -1.41
    Left
    -1.40
     lef
    -1.37
    left
    -1.30
     Right
    -1.29
     righ
    -1.28
    Right
    -1.25
    POSITIVE LOGITS
    ReusableCell
    0.55
     Grenz
    0.53
    yama
    0.49
    laştır
    0.46
    FormState
    0.45
     producteurs
    0.45
     باسم
    0.44
    ={({
    0.44
    ниця
    0.43
     sə
    0.42
    Activations Density 1.486%

    No Known Activations