© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16089
    Prev
    Next
    INDEX
    Explanations

    question words, especially when related to travel

    oai_token-act-pair · gemini-2.0-flash

    Tours and tourism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     referenties
    -0.50
    #+#
    -0.48
    thâu
    -0.47
     BoxFit
    -0.44
    calipsis
    -0.42
     initComponents
    -0.42
    Lähteet
    -0.42
    posedge
    -0.42
    NgModule
    -0.41
    łada
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    0.94
     poffe
    0.66
     tranſ
    0.65
     uſe
    0.61
     purpoſe
    0.60
     pleaſure
    0.59
    maran
    0.59
    ]));
    0.58
     ground
    0.57
     himſelf
    0.57
    Activations Density 3.474%

    No Known Activations