© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1710
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and general behaviors

    oai_token-act-pair · gemini-2.0-flash

    act

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     act
    -2.80
     Act
    -2.53
    Act
    -2.44
     acts
    -2.30
    act
    -2.30
     acted
    -2.13
     acting
    -2.05
     ACT
    -2.02
     Acts
    -1.95
    ACT
    -1.84
    POSITIVE LOGITS
     TextInputType
    0.69
    CloseOperation
    0.61
     behö
    0.55
     Powell
    0.50
    ẤT
    0.50
     igång
    0.49
    zijde
    0.49
     linkovi
    0.48
    ReusableCell
    0.47
    äsent
    0.46
    Activations Density 2.792%

    No Known Activations