© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15336
    Prev
    Next
    INDEX
    Explanations

    the word "interview", sometimes triggering on words near it as well

    oai_token-act-pair · gemini-2.0-flash

    interview

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ChildScrollView
    -0.83
    extAlignment
    -0.70
     ddelweddau
    -0.70
     gynhyrchwyd
    -0.69
    PerformLayout
    -0.65
     تانيه
    -0.65
    fitrión
    -0.63
     tartalomajánló
    -0.63
    webElementGuid
    -0.63
     Профиль
    -0.61
    POSITIVE LOGITS
     conducted
    0.50
     hóspedes
    0.47
     performed
    0.46
    Conduct
    0.45
     with
    0.45
     preocupa
    0.45
    CCP
    0.45
    smarty
    0.45
    біль
    0.44
    cin
    0.42
    Activations Density 1.879%

    No Known Activations