© 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. 13861
    Prev
    Next
    INDEX
    Explanations

    references to rivers

    oai_token-act-pair · gemini-2.0-flash

    names of locations or geographical features

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

    rivers

    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
    thâu
    -0.87
    Попис
    -0.78
     himſelf
    -0.73
    Хьажоргаш
    -0.71
    Vidite
    -0.69
    ьаж
    -0.69
     myſelf
    -0.68
     disambiguazione
    -0.67
     Jefus
    -0.67
    styleType
    -0.67
    POSITIVE LOGITS
     typelib
    0.69
    BagConstraints
    0.43
     Ka
    0.42
     stuk
    0.41
    た
    0.41
     beat
    0.40
    lined
    0.40
    물
    0.40
    ionali
    0.40
    чел
    0.40
    Activations Density 1.144%

    No Known Activations