© 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. 4090
    Prev
    Next
    INDEX
    Explanations

    the word "another"

    oai_token-act-pair · gemini-2.0-flash

    another

    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
     another
    -2.98
    another
    -2.64
    Another
    -2.31
     Another
    -2.27
     ANOTHER
    -1.86
     otra
    -1.51
    另一个
    -1.50
     otro
    -1.49
    另一种
    -1.41
    另一個
    -1.41
    POSITIVE LOGITS
    afone
    0.66
     
    0.59
    ander
    0.59
    lık
    0.56
     rest
    0.55
    $
    0.52
    t
    0.52
    preduce
    0.51
    bilt
    0.51
    okovic
    0.51
    Activations Density 2.081%

    No Known Activations