© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11785
    Prev
    Next
    INDEX
    Explanations

    words related to how people make evaluations and take action

    oai_token-act-pair · gemini-2.0-flash

    "make" variations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     propOrder
    -0.75
     CreateTagHelper
    -0.71
    +:+
    -0.67
    Personendaten
    -0.63
    URLException
    -0.63
    rawDesc
    -0.62
     Roskov
    -0.59
    DatabaseError
    -0.58
     jadx
    -0.57
    EndInit
    -0.56
    POSITIVE LOGITS
     made
    1.98
    made
    1.80
     Made
    1.68
    Made
    1.67
     MADE
    1.59
    make
    1.51
     make
    1.45
    making
    1.45
    MADE
    1.44
    Making
    1.39
    Activations Density 1.181%

    No Known Activations