© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4469
    Prev
    Next
    INDEX
    Explanations

    the words "proper/ly" and words related to "reduction in amount"

    oai_token-act-pair · gemini-2.0-flash

    proper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     properly
    -2.33
    Proper
    -2.31
     proper
    -2.31
    proper
    -2.27
    properly
    -2.23
     Proper
    -2.20
     PROPER
    -2.17
     Properly
    -2.09
     improperly
    -1.18
     correctement
    -1.06
    POSITIVE LOGITS
    bootstrapcdn
    0.63
     незавершена
    0.63
    waitKey
    0.54
    himu
    0.53
    cartes
    0.52
     jegy
    0.51
     suena
    0.50
    posedge
    0.50
     المعيارى
    0.50
     stepmother
    0.49
    Activations Density 1.378%

    No Known Activations