© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5303
    Prev
    Next
    INDEX
    Explanations

    words associated with risk, security, and legal or medical implications

    oai_token-act-pair · gemini-2.0-flash

    general observations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    enumi
    -0.55
    rupal
    -0.55
    enumii
    -0.54
     initComponents
    -0.52
     ролях
    -0.49
    WithIOException
    -0.48
    DockStyle
    -0.47
    BeNil
    -0.46
    Enllaces
    -0.44
    Varint
    -0.43
    POSITIVE LOGITS
     quite
    0.59
     Quite
    0.57
     发表于
    0.56
     strong
    0.54
    quite
    0.54
     cukup
    0.53
    Quite
    0.53
     immense
    0.52
     DbType
    0.52
    tagext
    0.52
    Activations Density 2.580%

    No Known Activations