© 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. 15266
    Prev
    Next
    INDEX
    Explanations

    the word "go" in various contexts, but most often with actions following it

    oai_token-act-pair · gemini-2.0-flash

    go

    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
     go
    -1.13
    Go
    -0.95
    go
    -0.89
     Go
    -0.88
     GO
    -0.87
     WENT
    -0.76
     goes
    -0.75
     went
    -0.75
    Went
    -0.74
     gone
    -0.73
    POSITIVE LOGITS
    İZ
    0.52
    TypedDataSet
    0.51
    meren
    0.49
    badlogic
    0.48
    sensi
    0.48
     beautiful
    0.47
    JspWriter
    0.47
     Codes
    0.47
    PYX
    0.46
     Natural
    0.45
    Activations Density 10.957%

    No Known Activations