© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10514
    Prev
    Next
    INDEX
    Explanations

    words frequently used as prepositions or conjunctions in film reviews

    oai_token-act-pair · gemini-2.0-flash

    diverse language terms and specific queries

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

    foreign language

    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
    ScopeManager
    -0.48
     térm
    -0.47
     onore
    -0.46
    TestingModule
    -0.44
     hijas
    -0.44
     partners
    -0.42
     Mahasiswa
    -0.42
     works
    -0.41
     Premios
    -0.40
    fml
    -0.40
    POSITIVE LOGITS
    Personensuche
    0.82
     незавершена
    0.75
    queryInterface
    0.69
    Espèce
    0.67
    OGND
    0.62
    ghijklmnop
    0.62
     Réponses
    0.61
    पया
    0.60
     nakalista
    0.60
    Lähteet
    0.60
    Activations Density 2.981%

    No Known Activations