© 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. 9925
    Prev
    Next
    INDEX
    Explanations

    negative opinions about things, especially with "too/only to"

    oai_token-act-pair · gemini-2.0-flash

    say "to"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.63
    PreferredItem
    -0.52
    AddTagHelper
    -0.51
    RunWith
    -0.50
     يتيمه
    -0.49
     MainAxisSize
    -0.49
     AssemblyCompany
    -0.48
    -------
    -0.47
     Partagez
    -0.46
    UTERS
    -0.45
    POSITIVE LOGITS
     to
    1.20
     чтобы
    0.67
     να
    0.66
    '},
    0.55
     để
    0.54
     ausz
    0.52
     untuk
    0.51
    ftagPool
    0.49
    }))
    0.49
    帖最后由
    0.48
    Activations Density 1.305%

    No Known Activations