© 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. 5423
    Prev
    Next
    INDEX
    Explanations

    mentions of the first person along with past tense verbs like "saw," "heard," and "seen."

    oai_token-act-pair · gemini-2.0-flash

    perception of sight/sound

    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
    SharedCtor
    -0.66
    
    -0.62
    
    -0.59
    assium
    -0.59
     use
    -0.56
     uſe
    -0.54
    ждый
    -0.53
     usage
    -0.53
    unculus
    -0.53
     Corcoran
    -0.50
    POSITIVE LOGITS
     sees
    0.62
     seen
    0.62
     seeing
    0.60
     vedea
    0.60
    Xna
    0.59
     saw
    0.58
     see
    0.57
    sees
    0.56
     See
    0.55
     voir
    0.55
    Activations Density 1.130%

    No Known Activations