© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4338
    Prev
    Next
    INDEX
    Explanations

    sentences expressing wants, needs, or desires

    oai_token-act-pair · gemini-2.0-flash

    desire, necessity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tayo
    -0.66
     kayo
    -0.61
    roned
    -0.57
    Ndr
    -0.57
    EndInit
    -0.57
     yourselves
    -0.57
     Reverso
    -0.57
     CURIAM
    -0.55
    orgio
    -0.55
    arXiv
    -0.54
    POSITIVE LOGITS
     my
    1.17
    my
    1.09
    My
    0.98
     My
    0.91
     miei
    0.85
     meines
    0.85
     моих
    0.84
     मेरे
    0.81
     minhas
    0.81
     meus
    0.81
    Activations Density 1.554%

    No Known Activations