© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14228
    Prev
    Next
    INDEX
    Explanations

    parts of names containing the letters 'an'

    oai_token-act-pair · gemini-2.0-flash

    Foreign locations/names

    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
     kasarigan
    -0.90
    sizeCache
    -0.79
    tagHelperRunner
    -0.79
    webElementXpaths
    -0.76
    Revenir
    -0.74
    protoimpl
    -0.74
    GraphicsUnit
    -0.70
    UnusedPrivate
    -0.69
    TypedDataSet
    -0.69
    :+:
    -0.68
    POSITIVE LOGITS
     кор
    0.47
    ir
    0.46
    tarea
    0.44
    RectangleBorder
    0.42
    zam
    0.40
    am
    0.40
    gesteld
    0.40
    irs
    0.40
    門
    0.39
    ribut
    0.39
    Activations Density 0.066%

    No Known Activations