© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6352
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with analysis.

    oai_token-act-pair · gemini-2.0-flash

    Lacking, deficiency

    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
     Ruy
    -0.53
     betweenstory
    -0.53
    featureID
    -0.49
    atoga
    -0.48
    łgor
    -0.48
    Diweddarwch
    -0.48
    frå
    -0.47
    (;;)
    -0.46
    ayama
    -0.45
    뀔
    -0.44
    POSITIVE LOGITS
     deficiencies
    1.20
     failures
    1.09
     shortcomings
    1.08
     lacking
    1.06
     deficient
    1.05
     failure
    1.05
     Defic
    1.04
     failings
    1.04
     deficiency
    1.02
     failing
    1.01
    Activations Density 2.006%

    No Known Activations