© 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. 6642
    Prev
    Next
    INDEX
    Explanations

    C/C++ code syntax and macros

    oai_token-act-pair · gemini-2.0-flash

    say "S" word

    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
    #!/
    -0.44
    طيع
    -0.44
    vold
    -0.43
     αυ
    -0.42
     phạm
    -0.42
    NSYLVANIA
    -0.41
    блоки
    -0.40
     []*
    -0.40
     transfé
    -0.40
    hion
    -0.39
    POSITIVE LOGITS
    verwijspagina
    0.96
    ValueStyle
    0.96
    ContentAsync
    0.88
    DockStyle
    0.87
    AutoScaleMode
    0.87
    хьтан
    0.87
     tartalomajánló
    0.83
    SharedCtor
    0.81
    +#+#
    0.80
     resourceCulture
    0.76
    Activations Density 3.742%

    No Known Activations