© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    the word "this" and words that follow "such"

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     this
    -3.27
    this
    -2.33
     questa
    -1.55
     этого
    -1.52
     questo
    -1.45
     цього
    -1.38
     này
    -1.38
     этой
    -1.38
     هذا
    -1.37
     acestui
    -1.37
    POSITIVE LOGITS
     Here
    0.57
    «
    0.53
    isa
    0.51
     «
    0.51
    zo
    0.49
    »
    0.49
    tics
    0.49
     sy
    0.48
    er
    0.47
    ("}\
    0.47
    Activations Density 3.121%

    No Known Activations