© 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. 13431
    Prev
    Next
    INDEX
    Explanations

    Swedish language and/or Swedish place names and Swedish biographical information

    oai_token-act-pair · gemini-2.0-flash

    Swedish language tokens

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

    Swedish 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
     disambiguazione
    -0.88
     blest
    -0.77
     itſelf
    -0.72
     becauſe
    -0.68
     Cæsar
    -0.66
     Shakspeare
    -0.66
    الحياه
    -0.64
     فريبيس
    -0.64
     Karsten
    -0.63
    はじめに
    -0.63
    POSITIVE LOGITS
     int
    0.44
     alla
    0.43
     och
    0.43
     vare
    0.39
     inte
    0.39
     att
    0.39
     refirió
    0.39
     nu
    0.39
     sucedido
    0.39
    ade
    0.38
    Activations Density 0.040%

    No Known Activations