© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2446
    Prev
    Next
    INDEX
    Explanations

    content about tickets, entitlements, sales, live events and digital rights

    oai_token-act-pair · gemini-2.0-flash

    ticket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ticket
    -0.79
     tickets
    -0.74
     TICKETS
    -0.67
    tickets
    -0.67
     Tickets
    -0.67
    Tickets
    -0.66
    ticket
    -0.65
    TICKETS
    -0.63
     Ticket
    -0.63
     bed
    -0.60
    POSITIVE LOGITS
    ंदीखरीदारी
    0.68
     समीक्षक
    0.65
     متعلقه
    0.63
     Nelle
    0.63
     fondament
    0.60
     Bucure
    0.59
    tagonist
    0.59
    </thead>
    0.59
    ieuses
    0.59
     للاسماء
    0.58
    Activations Density 15.251%

    No Known Activations