© 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. 4426
    Prev
    Next
    INDEX
    Explanations

    words that connect or belong to a specific list.

    oai_token-act-pair · gemini-2.0-flash

    comma and "and"

    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
    žiai
    -0.47
     cebolla
    -0.46
     Albert
    -0.45
     sirven
    -0.45
    ItemBackground
    -0.44
     Puig
    -0.44
    univ
    -0.44
     servem
    -0.43
    layouts
    -0.43
    Albert
    -0.43
    POSITIVE LOGITS
     ExecuteAsync
    0.60
     архивлан
    0.60
    autorelease
    0.58
     FontWeight
    0.57
    DockStyle
    0.56
    httphttps
    0.56
     AttributeSet
    0.55
     lenker
    0.55
    OrNil
    0.54
    awakeFromNib
    0.54
    Activations Density 3.555%

    No Known Activations