© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10276
    Prev
    Next
    INDEX
    Explanations

    topics related to information being leaked or obtained in secret

    oai_token-act-pair · gemini-2.0-flash

    got

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    awtextra
    -0.63
    AnchorStyles
    -0.58
    <bos>
    -0.57
    AndEndTag
    -0.57
    WaitGroup
    -0.56
    üz
    -0.54
    ChildScrollView
    -0.53
    kl
    -0.52
     समीक्षाओं
    -0.52
    shadowRadius
    -0.52
    POSITIVE LOGITS
     poffible
    0.52
     reaſon
    0.51
     myſelf
    0.49
     vielmehr
    0.49
     poffe
    0.49
     raiſ
    0.49
    olstadt
    0.47
    expandindo
    0.47
     secretly
    0.47
     Efq
    0.46
    Activations Density 0.322%

    No Known Activations