© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11384
    Prev
    Next
    INDEX
    Explanations

    words related to circumstances, lab tests, or physical state

    oai_token-act-pair · gemini-2.0-flash

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     condition
    -2.72
     conditions
    -2.70
     Conditions
    -2.52
     Condition
    -2.48
    conditions
    -2.36
    Condition
    -2.36
    condition
    -2.31
    Conditions
    -2.30
     CONDITIONS
    -2.20
     CONDITION
    -2.19
    POSITIVE LOGITS
     astray
    0.64
     swears
    0.59
     FileInputStream
    0.56
    mless
    0.53
    parliament
    0.52
     gants
    0.52
     traditionally
    0.51
     swear
    0.50
     sworn
    0.50
     prouver
    0.50
    Activations Density 5.138%

    No Known Activations