© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7405
    Prev
    Next
    INDEX
    Explanations

    scientific writing and sexually explicit actions.

    oai_token-act-pair · gemini-2.0-flash

    standing

    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
     myſelf
    -0.87
     يتيمه
    -0.86
     itſelf
    -0.86
    AndEndTag
    -0.84
    ValueStyle
    -0.84
    IndentedString
    -0.82
     BorderSide
    -0.82
     ―――――
    -0.82
     ſind
    -0.81
    GEBURTSDATUM
    -0.81
    POSITIVE LOGITS
     standing
    0.61
     Stand
    0.60
     stand
    0.59
     (
    0.51
    Stand
    0.50
    stand
    0.49
     stood
    0.49
     stands
    0.48
     STAND
    0.47
     
    0.47
    Activations Density 8.700%

    No Known Activations