© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3094
    Prev
    Next
    INDEX
    Explanations

    the word "solutions" and sometimes flags the word "exist" nearby

    oai_token-act-pair · gemini-2.0-flash

    solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    solutions
    -1.00
     solution
    -0.95
    Lösung
    -0.92
     solución
    -0.92
    solution
    -0.92
     solutions
    -0.91
     propOrder
    -0.90
     Solution
    -0.87
    ercises
    -0.84
    Solutions
    -0.84
    POSITIVE LOGITS
    dy
    0.65
     sopp
    0.64
    r
    0.64
    sy
    0.63
    SY
    0.62
    hl
    0.62
    +:+
    0.62
    alie
    0.60
    die
    0.60
    I
    0.60
    Activations Density 0.668%

    No Known Activations