© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15612
    Prev
    Next
    INDEX
    Explanations

    words related to travel opportunities, especially sampling and taking tours

    oai_token-act-pair · gemini-2.0-flash

    words related to wine tasting and tourism

    np_token-act-pair-logits · gpt-4o-mini

    Actions, options, experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    berdayakan
    -0.69
     Houſe
    -0.64
     ſtate
    -0.62
     ſeveral
    -0.61
     étoit
    -0.60
     poffible
    -0.60
     Majefty
    -0.60
     Anſ
    -0.59
     mourut
    -0.59
     Eſ
    -0.59
    POSITIVE LOGITS
    TemporalType
    0.53
    verwijspagina
    0.52
     p
    0.52
    ългария
    0.51
     revel
    0.50
     let
    0.49
    UnsafeEnabled
    0.49
    DebuggerNonUser
    0.48
    lismo
    0.48
     sample
    0.47
    Activations Density 0.847%

    No Known Activations