© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8995
    Prev
    Next
    INDEX
    Explanations

    words related to gambling, along with some other random phrases such as "very" followed by a possessive and "page"

    oai_token-act-pair · gemini-2.0-flash

    casino

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    //
    -0.48
     تضيفلها
    -0.45
     general
    -0.45
    nloa
    -0.44
     sanitaires
    -0.43
    Ting
    -0.42
     لينك
    -0.42
     Ind
    -0.41
    Tracce
    -0.40
    Demografía
    -0.40
    POSITIVE LOGITS
     Roskov
    0.74
    出版年
    0.69
    abestanden
    0.66
     Extragalactic
    0.60
     ſche
    0.57
     Ammon
    0.56
     Shakspeare
    0.56
     sumpay
    0.56
     inoxidable
    0.55
     муніципалі
    0.55
    Activations Density 0.028%

    No Known Activations