© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7757
    Prev
    Next
    INDEX
    Explanations

    the word "gain" or similar words referring to a positive change

    oai_token-act-pair · gemini-2.0-flash

    gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     gain
    -2.92
     Gain
    -2.77
    gain
    -2.63
    Gain
    -2.61
     gained
    -2.41
     gains
    -2.39
     GAIN
    -2.27
     gaining
    -2.22
     Gains
    -2.03
    gains
    -1.98
    POSITIVE LOGITS
     financement
    0.52
    setImageBitmap
    0.51
    clerosis
    0.50
    endal
    0.49
    Aktualisiert
    0.49
    loài
    0.47
    Obrázky
    0.47
     financiamiento
    0.47
     chronique
    0.47
     legend
    0.45
    Activations Density 0.367%

    No Known Activations