© 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. 9543
    Prev
    Next
    INDEX
    Explanations

    words expressing preferences, opinion or identity

    oai_token-act-pair · gemini-2.0-flash

    roles in collaborative contexts

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

    types of people

    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
     disambiguazione
    -0.83
     getUsers
    -0.70
     quienes
    -0.69
     którzy
    -0.68
    WithIOException
    -0.63
     bearers
    -0.63
    Hochspringen
    -0.62
    getUsers
    -0.61
     pilots
    -0.61
     captains
    -0.60
    POSITIVE LOGITS
     researcher
    1.14
     participant
    1.14
     member
    1.13
     supporter
    1.09
     performer
    1.09
     player
    1.09
     person
    1.05
     colleague
    1.02
     athlete
    1.02
     worker
    1.02
    Activations Density 3.407%

    No Known Activations