© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7539
    Prev
    Next
    INDEX
    Explanations

    pronouns and words related to people interacting

    oai_token-act-pair · gemini-2.0-flash

    variations of "go"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ostavi
    -0.77
    ViewFeatures
    -0.73
    contentLoaded
    -0.73
     pinulongan
    -0.67
    __(/*!
    -0.65
     '{@
    -0.63
     ExecuteAsync
    -0.63
    ]),
    -0.62
    ContentAsync
    -0.60
    ValueStyle
    -0.60
    POSITIVE LOGITS
     goes
    2.47
     go
    2.44
    goes
    2.11
     Goes
    2.00
     went
    1.89
    go
    1.88
    Go
    1.84
     Go
    1.84
    Goes
    1.81
     going
    1.74
    Activations Density 3.376%

    No Known Activations