© 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. 7079
    Prev
    Next
    INDEX
    Explanations

    the phrase "into contact", and also sentences with the word "heatpipes" in them

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'contact'

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

    contact

    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
    PhysRevD
    -0.52
     stolz
    -0.50
     Pup
    -0.46
    PopMatrix
    -0.46
    OGND
    -0.46
    ziplin
    -0.46
    //=
    -0.44
    oque
    -0.43
     unknownFields
    -0.42
    loit
    -0.41
    POSITIVE LOGITS
     contact
    2.75
    contact
    2.39
     Contact
    2.33
    Contact
    2.23
     CONTACT
    2.11
     contacts
    2.00
     contacto
    1.94
    CONTACT
    1.89
     Contacts
    1.82
     contacting
    1.73
    Activations Density 2.336%

    No Known Activations