© 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. 6795
    Prev
    Next
    INDEX
    Explanations

    geographic place names near Texas, especially city names

    oai_token-act-pair · gemini-2.0-flash

    words in non-English scripts

    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
     Bogen
    -0.45
    ModelForm
    -0.43
     دار
    -0.43
    BindingSource
    -0.43
     Diakses
    -0.42
     endforeach
    -0.41
    nlm
    -0.41
    Dés
    -0.41
    CppCodeGen
    -0.41
     noun
    -0.40
    POSITIVE LOGITS
    الحياه
    0.76
    
    0.64
     كومونز
    0.60
    OGND
    0.59
     للاسماء
    0.59
    enumii
    0.58
    ########.
    0.57
     فريبيس
    0.57
    lankton
    0.54
    outé
    0.54
    Activations Density 2.169%

    No Known Activations