© 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. 10510
    Prev
    Next
    INDEX
    Explanations

    the word "investors" and words associated with investment or progress

    oai_token-act-pair · gemini-2.0-flash

    investors

    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
     purpoſe
    -1.84
     ſtate
    -1.73
     pleaſure
    -1.66
     Monfieur
    -1.63
     myſelf
    -1.62
     themſelves
    -1.59
     Majefty
    -1.57
     avoient
    -1.55
     quæ
    -1.55
     enfans
    -1.54
    POSITIVE LOGITS
    ing
    1.19
     
    0.90
     I
    0.85
    ING
    0.84
     B
    0.84
     R
    0.84
     Por
    0.82
     Ma
    0.82
     —
    0.81
     Sur
    0.81
    Activations Density 2.069%

    No Known Activations