© 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. 10851
    Prev
    Next
    INDEX
    Explanations

    negative numbers in the text

    oai_token-act-pair · gemini-2.0-flash

    numbers and calculations

    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
    ruptedException
    -0.62
     ModelAndView
    -0.55
    rceil
    -0.54
    GAD
    -0.49
    WillAppear
    -0.48
    телно
    -0.47
    dotto
    -0.47
    PreExecute
    -0.46
    mesan
    -0.45
    RunWith
    -0.45
    POSITIVE LOGITS
    principalColumn
    0.62
    mybatisplus
    0.59
    migrationBuilder
    0.58
    ientí
    0.55
    municipi
    0.54
    sius
    0.53
     []:
    0.52
     otomatig
    0.50
    ctive
    0.50
    Odkazy
    0.50
    Activations Density 1.829%

    No Known Activations