© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15321
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with deduction and inference

    oai_token-act-pair · gemini-2.0-flash

    possibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     do
    -0.74
     could
    -0.66
     might
    -0.62
     shall
    -0.60
     must
    -0.59
     may
    -0.59
     Do
    -0.57
     can
    -0.57
     Must
    -0.54
    imp
    -0.53
    POSITIVE LOGITS
    AndEndTag
    0.75
     utafitiHapana
    0.75
     فريبيس
    0.65
     itſelf
    0.65
    NewGuid
    0.64
    Према
    0.64
    :+:
    0.62
     JpaRepository
    0.60
     themſelves
    0.60
     preſent
    0.59
    Activations Density 5.454%

    No Known Activations