© 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. 10244
    Prev
    Next
    INDEX
    Explanations

    words related to forecasts and estimation

    oai_token-act-pair · gemini-2.0-flash

    predict

    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
     myſelf
    -1.48
     ſche
    -1.41
     faſt
    -1.40
     itſelf
    -1.38
     raiſ
    -1.35
     iſt
    -1.33
     pleaſure
    -1.30
     purpoſe
    -1.30
     ſta
    -1.28
     ―――――
    -1.28
    POSITIVE LOGITS
     démocr
    1.90
     idéia
    1.81
     vérit
    1.80
     precisione
    1.77
     tromper
    1.76
     vectorielles
    1.73
     fermés
    1.73
     enfans
    1.71
     lèvres
    1.69
     colorés
    1.69
    Activations Density 5.732%

    No Known Activations