© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12819
    Prev
    Next
    INDEX
    Explanations

    a mix of random words and numbers, possibly related to copyright or document structure, and names with numbers

    oai_token-act-pair · gemini-2.0-flash

    Excerpts

    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
    ConstraintMaker
    -1.20
    SourceChecksum
    -1.14
     Мексичка
    -1.07
    complexContent
    -1.05
    tagHelperRunner
    -1.02
    Personensuche
    -1.00
    AnimationsModule
    -0.97
     initComponents
    -0.96
    GraphicsUnit
    -0.96
    DeleteBehavior
    -0.96
    POSITIVE LOGITS
    ly
    0.56
    回
    0.46
    。
    0.45
    自
    0.43
    ally
    0.43
    nya
    0.42
    ns
    0.41
    ed
    0.41
     demain
    0.41
    ya
    0.41
    Activations Density 0.114%

    No Known Activations