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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8175
    Prev
    Next
    INDEX
    Explanations

    words related to wanting to work with someone

    oai_token-act-pair · gemini-2.0-flash

    Marketing and recommendations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tvguidetime
    -0.68
    SequentialGroup
    -0.64
    клопе
    -0.62
    ærke
    -0.61
    quois
    -0.61
    Билгалдахарш
    -0.60
    RenderAtEndOf
    -0.58
    files
    -0.57
     surla
    -0.56
    Stream
    -0.56
    POSITIVE LOGITS
    =$?
    0.50
     MainAxisSize
    0.45
     policia
    0.42
    AnchorTagHelper
    0.42
    Portail
    0.39
    SharedDtor
    0.39
     resourceCulture
    0.39
    DispatchToProps
    0.38
    >--}}
    0.36
     للمعارف
    0.36
    Activations Density 8.624%

    No Known Activations