© 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. 4651
    Prev
    Next
    INDEX
    Explanations

    words related to medical cases or international relations/conflict

    oai_token-act-pair · gemini-2.0-flash

    turning

    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
    tvguidetime
    -0.67
    verwijspagina
    -0.66
    Попис
    -0.62
     informée
    -0.60
    EDEFAULT
    -0.58
     autorytatywna
    -0.57
    UrlResolution
    -0.54
    anskje
    -0.54
    học
    -0.54
    viewDidLoad
    -0.54
    POSITIVE LOGITS
     turn
    0.94
    turn
    0.87
     turning
    0.84
     deterioration
    0.84
    Turn
    0.82
     turns
    0.81
    TURN
    0.79
     Turning
    0.78
     Turn
    0.73
    Turning
    0.73
    Activations Density 0.893%

    No Known Activations