© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7572
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making, including preferences, advice, and trends.

    oai_token-act-pair · gemini-2.0-flash

    instead

    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
    wiada
    -0.64
    PerformLayout
    -0.60
    quelize
    -0.59
    izoen
    -0.58
     Infórmanos
    -0.55
     Courant
    -0.55
    ALG
    -0.55
    UMBUS
    -0.54
    buro
    -0.54
    bege
    -0.54
    POSITIVE LOGITS
     instead
    3.23
     rather
    3.11
    instead
    2.98
    Instead
    2.83
     Instead
    2.78
    rather
    2.75
     Rather
    2.63
    Rather
    2.63
     plutôt
    2.39
     zamiast
    2.28
    Activations Density 13.905%

    No Known Activations