© 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. 14339
    Prev
    Next
    INDEX
    Explanations

    sentences with multiple personal pronouns referring to multiple people

    oai_token-act-pair · gemini-2.0-flash

    technical terms and 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
     hasn
    -0.52
    íncipe
    -0.49
     Didn
    -0.49
     Jefus
    -0.48
     solaire
    -0.48
     houſe
    -0.48
     espac
    -0.48
     wasn
    -0.48
    wasan
    -0.47
    ]='\
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.63
    Naissance
    0.52
    Datuak
    0.52
     חיצוניים
    0.50
     referenties
    0.50
    المناصب
    0.50
    原始内容存档于
    0.50
    ">{{
    0.49
    CloseOperation
    0.49
    Geplaatst
    0.49
    Activations Density 2.183%

    No Known Activations