© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12790
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to social programs, treatment, and intervention

    oai_token-act-pair · gemini-2.0-flash

    terms related to medical programs and interventions

    np_token-act-pair-logits · gpt-4o-mini

    Health intervention studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     Bobo
    -0.44
     SwitchCompat
    -0.42
     murni
    -0.39
    danno
    -0.38
    PII
    -0.38
    claw
    -0.38
     forced
    -0.37
     Italijani
    -0.37
    pheny
    -0.37
     HARRISON
    -0.37
    POSITIVE LOGITS
    archiviato
    0.71
    PageRoute
    0.67
     Behav
    0.66
     Verhaltens
    0.65
    expandindo
    0.64
    GEBURTSDATUM
    0.64
     Rtl
    0.63
    nino
    0.62
    Geplaatst
    0.62
     MainAxisSize
    0.62
    Activations Density 2.376%

    No Known Activations