© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4599
    Prev
    Next
    INDEX
    Explanations

    words related to psychology, therapy, childhood trauma, and abuse

    oai_token-act-pair · gemini-2.0-flash

    loss/tragedy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     typelib
    -0.69
    ponses
    -0.58
    )}
    -0.56
    ThroughAttribute
    -0.55
    bahar
    -0.55
    PreferredItem
    -0.55
     continúas
    -0.55
    reportWebVitals
    -0.55
    HideFlags
    -0.54
    tillon
    -0.53
    POSITIVE LOGITS
     loss
    0.84
     losses
    0.72
     tragedy
    0.71
     lost
    0.67
     sufrió
    0.67
    loss
    0.66
     incident
    0.66
     tragedies
    0.65
     tragic
    0.64
     damage
    0.64
    Activations Density 3.725%

    No Known Activations