© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 10169
    Prev
    Next
    INDEX
    Explanations

    narratives involving solving a mystery or problem

    oai_token-act-pair · gemini-2.0-flash

    solve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     виправивши
    -0.69
    Билгалдахарш
    -0.68
    setVerticalGroup
    -0.67
     beginnetje
    -0.66
     transférez
    -0.65
     Вікі
    -0.65
    OGND
    -0.65
     Италијани
    -0.64
    tinyos
    -0.63
     فريبيس
    -0.63
    POSITIVE LOGITS
     solve
    1.19
     solving
    1.18
     mystery
    1.15
     solved
    1.13
     puzzle
    1.09
     Solving
    1.08
     solves
    1.06
     unsolved
    1.05
     Solve
    1.03
     puzzles
    1.03
    Activations Density 1.590%

    No Known Activations