© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14023
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate relationships, like "roles currently" or "suited to have".

    oai_token-act-pair · gemini-2.0-flash

    assume

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     role
    -0.84
    role
    -0.72
    ROLE
    -0.65
    Role
    -0.65
     ROLE
    -0.63
     Role
    -0.63
    WebServlet
    -0.62
     roles
    -0.59
    ActionButton
    -0.59
     Efq
    -0.58
    POSITIVE LOGITS
     assume
    1.85
     assumption
    1.73
     assumed
    1.73
     assumes
    1.70
     assuming
    1.70
    assume
    1.59
    assumption
    1.47
     assumptions
    1.46
    assumed
    1.45
     Assume
    1.31
    Activations Density 3.838%

    No Known Activations