© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3119
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons and questions involving "is", "or", and "which".

    oai_token-act-pair · gemini-2.0-flash

    Number/size comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     propios
    -0.42
     câteva
    -0.40
     acabou
    -0.38
     fantasmas
    -0.36
     próprias
    -0.36
    ribusiness
    -0.35
    sikal
    -0.35
    ARB
    -0.35
    熟悉的
    -0.35
     dilengkapi
    -0.35
    POSITIVE LOGITS
     numberOfRows
    0.92
     height
    0.84
     distance
    0.79
     للاسماء
    0.79
     length
    0.79
     width
    0.77
     Height
    0.74
    Personensuche
    0.73
    Aholisi
    0.71
     salary
    0.71
    Activations Density 8.915%

    No Known Activations