© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8352
    Prev
    Next
    INDEX
    Explanations

    academic writing that includes descriptions of scientific studies and references to them.

    oai_token-act-pair · gemini-2.0-flash

    first-person references

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     AssemblyProduct
    -0.85
    AndEndTag
    -0.73
     للاسماء
    -0.72
     CommonModule
    -0.70
    LookAnd
    -0.68
     Geraadpleegd
    -0.67
    ConstraintMaker
    -0.65
     '\\;'
    -0.64
    nasel
    -0.60
     betweenstory
    -0.59
    POSITIVE LOGITS
     Me
    0.69
    Me
    0.64
     me
    0.60
    pushFollow
    0.52
    me
    0.46
    MetaType
    0.45
    meier
    0.45
     mia
    0.45
    marsh
    0.44
     Veen
    0.44
    Activations Density 3.238%

    No Known Activations