© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    places in the UK, especially London

    oai_token-act-pair · gemini-2.0-flash

    references to London

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

    London

    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
    apunov
    -0.49
     ComVisible
    -0.48
    gebob
    -0.45
    Hag
    -0.45
    amu
    -0.43
    sej
    -0.42
     cá
    -0.42
     nisso
    -0.41
    Demografie
    -0.41
    StoryboardSegue
    -0.40
    POSITIVE LOGITS
    קישורים
    0.71
    Tazama
    0.68
    Erreferentziak
    0.66
    Atsauces
    0.64
    曖昧さ回避
    0.62
    wój
    0.60
    তথ্যসূত্র
    0.60
     invokingState
    0.59
    tvguidetime
    0.59
     Welsh
    0.59
    Activations Density 0.301%

    No Known Activations