© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11696
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and medical topics, especially in the context of prisons and incarceration.

    oai_token-act-pair · gemini-2.0-flash

    Medical, phone, battery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Efq
    -1.32
     myſelf
    -1.23
     Monfieur
    -1.20
     Jefus
    -1.16
     whoſe
    -1.15
     Theſe
    -1.14
     becauſe
    -1.07
     poffible
    -1.06
     himſelf
    -1.04
     againſt
    -1.00
    POSITIVE LOGITS
     work
    0.47
     v
    0.40
     subs
    0.40
     */,
    0.39
     cho
    0.39
     po
    0.38
     дело
    0.38
    work
    0.37
     lo
    0.36
    pril
    0.36
    Activations Density 3.361%

    No Known Activations