© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15888
    Prev
    Next
    INDEX
    Explanations

    a variety of words with no clear common theme, it seems random

    oai_token-act-pair · gemini-2.0-flash

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     confiable
    -0.99
     flavorful
    -0.96
    ônicos
    -0.95
     harbors
    -0.91
    Neighbors
    -0.91
     favorably
    -0.91
    ônico
    -0.90
     parlor
    -0.90
    AVOR
    -0.89
     Neighbors
    -0.88
    POSITIVE LOGITS
    Whilst
    1.42
     Whilst
    1.34
     realised
    1.16
     recognised
    1.15
     whilst
    1.13
     tyres
    1.12
     specialises
    1.11
     realise
    1.10
     recognise
    1.09
     recognises
    1.09
    Activations Density 3.681%

    No Known Activations