© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10493
    Prev
    Next
    INDEX
    Explanations

    what could possibly be the weirdest collection of stuff ever, including a scroll function in code, random numbers, and unicode

    oai_token-act-pair · gemini-2.0-flash

    website data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    UnknownFieldSet
    -0.68
    évaluateur
    -0.63
    ]='\
    -0.58
    IUrlHelper
    -0.58
    DockStyle
    -0.57
     estimés
    -0.56
    "]);
    -0.53
     ujednoznacz
    -0.52
    лот
    -0.50
    aarrggbb
    -0.50
    POSITIVE LOGITS
    ########.
    0.65
    unmodifiable
    0.56
    DotNetBar
    0.54
    ětí
    0.53
    ̣i
    0.52
    EndProject
    0.51
     الذات
    0.49
    anonymous
    0.49
     inutile
    0.49
     precondition
    0.48
    Activations Density 0.973%

    No Known Activations