© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1709
    Prev
    Next
    INDEX
    Explanations

    the word "room" or words that can be interpreted as a place

    oai_token-act-pair · gemini-2.0-flash

    room

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     oprot
    -0.58
     casco
    -0.55
    tvguidetime
    -0.54
    setItems
    -0.54
    vmware
    -0.52
     monaster
    -0.52
     STUDIO
    -0.52
     studio
    -0.52
    はじめに
    -0.51
    cises
    -0.49
    POSITIVE LOGITS
    BeginInit
    0.66
    ArgumentParser
    0.51
    tangentMode
    0.50
    ThroughAttribute
    0.50
    AndroidJUnit
    0.49
    MergeFrom
    0.47
     skirts
    0.47
    </thead>
    0.47
     CreateTagHelper
    0.46
    κτηρισ
    0.45
    Activations Density 5.686%

    No Known Activations