© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 871
    Prev
    Next
    INDEX
    Explanations

    legal documents and code sections.

    oai_token-act-pair · gemini-2.0-flash

    legal code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     row
    -0.53
     collectons
    -0.53
    шкан
    -0.49
    didReceive
    -0.49
    melte
    -0.48
     گیا
    -0.46
     szeret
    -0.44
     rows
    -0.44
    stonia
    -0.44
    +$
    -0.44
    POSITIVE LOGITS
    Geplaatst
    0.66
    原始内容存档于
    0.64
     فريبيس
    0.61
    VideoCapture
    0.57
    ंदीखरीदारी
    0.57
    principalTable
    0.56
     entanto
    0.56
    olastic
    0.55
    jgl
    0.53
    getMinutes
    0.53
    Activations Density 2.236%

    No Known Activations