© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15467
    Prev
    Next
    INDEX
    Explanations

    the preposition "out" and words associated with it

    oai_token-act-pair · gemini-2.0-flash

    Movement, often physically up/out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    //
    -0.63
    /*
    -0.59
    Spoljašnje
    -0.59
    #
    -0.58
     Pilgri
    -0.56
     Thessal
    -0.56
    middels
    -0.54
     Pompey
    -0.52
     Cicero
    -0.51
    хьтан
    -0.51
    POSITIVE LOGITS
    uzzi
    0.50
     particular
    0.49
     exp
    0.48
    ussen
    0.47
     ''
    0.46
     Ant
    0.46
     Camp
    0.45
     >=",
    0.45
    หว่าง
    0.44
     Rosen
    0.44
    Activations Density 3.202%

    No Known Activations