© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12855
    Prev
    Next
    INDEX
    Explanations

    words related to attempts, aims, and direction

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ReusableCell
    -0.80
     فريبيس
    -0.71
     leaſt
    -0.65
    ništvo
    -0.63
    Predecesor
    -0.62
     pleaſure
    -0.62
     whoſe
    -0.61
     raiſ
    -0.59
     purpoſe
    -0.59
    PerformLayout
    -0.58
    POSITIVE LOGITS
     at
    2.86
     At
    1.59
    At
    1.57
    at
    1.50
     tại
    1.44
     AT
    0.94
     	e
    0.88
    AtIndex
    0.84
    Tại
    0.82
     presso
    0.80
    Activations Density 1.997%

    No Known Activations