© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6747
    Prev
    Next
    INDEX
    Explanations

    keywords in a Chinese language processing or dictionary context

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code references

    np_token-act-pair-logits · gpt-4o-mini

    technical and scientific texts

    np_max-act-logits · gemini-2.0-flash
    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
    GOTREF
    -0.58
     with
    -0.54
     Italij
    -0.52
    bootstrapcdn
    -0.52
    meyen
    -0.51
     ten
    -0.50
    inhos
    -0.49
    határoz
    -0.48
     while
    -0.48
    ngOn
    -0.48
    POSITIVE LOGITS
    endphp
    0.60
     metabol
    0.60
     disambiguazione
    0.55
     RDC
    0.52
     PPA
    0.52
    ModelForm
    0.50
     """
    0.49
     *)__
    0.49
     MEA
    0.48
    WithIOException
    0.48
    Activations Density 1.707%

    No Known Activations