© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5970
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and bibliographic references

    oai_token-act-pair · gemini-2.0-flash

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     iprot
    -0.50
    Portail
    -0.50
    fromnode
    -0.43
    Team
    -0.43
     Team
    -0.43
    loyment
    -0.42
    ğini
    -0.41
    pushFollow
    -0.40
     familiar
    -0.40
    cop
    -0.40
    POSITIVE LOGITS
    Hentet
    0.91
     وتسجيلات
    0.76
    ValueGeneration
    0.74
    GraphicsUnit
    0.70
    setViewportView
    0.67
     disambiguazione
    0.65
    +#+#
    0.63
     Tobi
    0.62
    ellschaft
    0.62
     ujednoznacz
    0.62
    Activations Density 3.391%

    No Known Activations