© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13561
    Prev
    Next
    INDEX
    Explanations

    phrases related to being careful or taking care

    oai_token-act-pair · gemini-2.0-flash

    caution and care

    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
     A
    -0.50
    jahtera
    -0.50
     admission
    -0.49
     grades
    -0.48
     Admission
    -0.46
     voti
    -0.45
     sat
    -0.45
    sat
    -0.44
     U
    -0.44
     credits
    -0.43
    POSITIVE LOGITS
     pleaſure
    1.07
     myſelf
    1.04
     purpoſe
    1.03
     ſeveral
    1.03
     Theſe
    1.02
     itſelf
    1.00
     ſever
    0.96
     Majefty
    0.94
     raiſ
    0.94
     Houſe
    0.93
    Activations Density 0.783%

    No Known Activations