© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12686
    Prev
    Next
    INDEX
    Explanations

    the word "pass" followed by certain prepositions, especially "on" or "by".

    oai_token-act-pair · gemini-2.0-flash

    the word "pass"

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

    pass

    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
    kuuta
    -0.54
     StatelessWidget
    -0.48
    ReusableCell
    -0.48
     pass
    -0.47
     understatement
    -0.46
    thus
    -0.45
     AssemblyTitle
    -0.45
     Passage
    -0.45
     Wrench
    -0.43
    gdx
    -0.43
    POSITIVE LOGITS
    UnsafeEnabled
    0.68
    IUrlHelper
    0.66
     незавершена
    0.66
    Personensuche
    0.65
     AssemblyCulture
    0.64
    featureID
    0.62
    ])));
    0.60
    twimg
    0.57
    XmlAccessType
    0.56
     GreatSchools
    0.56
    Activations Density 3.510%

    No Known Activations