© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8274
    Prev
    Next
    INDEX
    Explanations

    the phrase "check out"

    oai_token-act-pair · gemini-2.0-flash

    the word "check" and related commands

    np_token-act-pair-logits · gpt-4o-mini

    check

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    meaux
    -0.50
     look
    -0.50
     looking
    -0.47
     investigate
    -0.46
    bium
    -0.46
     Web
    -0.45
    /*
    -0.45
     pat
    -0.44
     evaluate
    -0.44
    oshin
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.67
    исленность
    0.66
     MotionEvent
    0.64
     InputDecoration
    0.64
     BorderRadius
    0.61
    routeProvider
    0.60
    sumowanie
    0.59
    StoryboardSegue
    0.59
    InitVars
    0.58
     theirs
    0.57
    Activations Density 0.545%

    No Known Activations