© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    words that indicate uncertain or speculative situations

    oai_token-act-pair · 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
     we
    -1.35
     me
    -1.30
     us
    -1.13
     nous
    -1.05
     нами
    -1.04
    We
    -1.03
     our
    -1.00
     We
    -0.98
     conmigo
    -0.98
     kami
    -0.97
    POSITIVE LOGITS
     defaultstate
    0.92
     StatefulWidget
    0.89
     BoxFit
    0.88
     }}"></
    0.87
     oprot
    0.86
     noqa
    0.85
    CloseOperation
    0.84
     يتيمه
    0.84
     him
    0.84
    rungsseite
    0.83
    Activations Density 3.911%

    No Known Activations