© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13613
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    family relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    OGND
    -0.94
    LookAnd
    -0.84
    GEBURTS
    -0.78
    MethodManager
    -0.76
    GEBURTSDATUM
    -0.73
    出版年
    -0.71
     архивлан
    -0.69
     Meksiku
    -0.69
    دانشنامهٔ
    -0.69
     otomatig
    -0.68
    POSITIVE LOGITS
     loving
    0.47
     driving
    0.43
     des
    0.43
     nhiêu
    0.42
     d
    0.42
     love
    0.42
     partner
    0.41
     belief
    0.41
     der
    0.40
     best
    0.40
    Activations Density 0.141%

    No Known Activations