© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7085
    Prev
    Next
    INDEX
    Explanations

    the word "right" with varying levels of punctuation, and the word "ok".

    oai_token-act-pair · gemini-2.0-flash

    agreement

    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
    uang
    -0.58
     télécommande
    -0.55
    leria
    -0.54
    wikia
    -0.52
     réputation
    -0.52
    мани
    -0.50
    eavor
    -0.50
    ORN
    -0.50
    BibitemOpen
    -0.48
    бище
    -0.48
    POSITIVE LOGITS
     ok
    1.28
     OK
    1.25
    Ok
    1.20
     alright
    1.20
     okay
    1.16
    OK
    1.08
     Ok
    1.08
    alright
    1.04
     Alright
    1.04
     OKAY
    1.03
    Activations Density 0.769%

    No Known Activations