© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7481
    Prev
    Next
    INDEX
    Explanations

    instances where the user indicates they have tried to find information themselves.

    oai_token-act-pair · gemini-2.0-flash

    search

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    edi
    -0.44
    فس
    -0.43
     capire
    -0.42
    jspb
    -0.41
    hiran
    -0.41
     waived
    -0.41
    ULD
    -0.40
     conservé
    -0.40
     principes
    -0.40
     humaine
    -0.40
    POSITIVE LOGITS
     search
    2.31
     Search
    1.99
    search
    1.92
    Search
    1.90
     SEARCH
    1.88
     searches
    1.85
     searching
    1.84
     searched
    1.76
    SEARCH
    1.71
     Searching
    1.70
    Activations Density 0.866%

    No Known Activations