© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6726
    Prev
    Next
    INDEX
    Explanations

    place names combined with suffixes or prefixes or other place names.

    oai_token-act-pair · gemini-2.0-flash

    locations, legal, historical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    webElementXpaths
    -0.72
    sidemargin
    -0.71
    addGap
    -0.71
    "}")
    -0.70
    ukov
    -0.69
     NSCoder
    -0.69
    ]='\
    -0.68
    ]+=
    -0.68
     незавершена
    -0.68
    ]--;
    -0.66
    POSITIVE LOGITS
     متعلقه
    0.57
    seamnă
    0.52
     brancas
    0.48
     linho
    0.48
     ddelweddau
    0.47
    horabuena
    0.47
     varandra
    0.46
     marinho
    0.45
    bbene
    0.42
     igenom
    0.41
    Activations Density 5.656%

    No Known Activations