© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13916
    Prev
    Next
    INDEX
    Explanations

    words relating to indian food ingredients, particularly sweets, used to make offerings

    oai_token-act-pair · gemini-2.0-flash

    food ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     confronti
    -0.68
     död
    -0.65
     asiatique
    -0.63
     plads
    -0.63
     jorden
    -0.60
     inconn
    -0.59
     fratelli
    -0.59
     africains
    -0.59
     gång
    -0.58
     niedersachsen
    -0.58
    POSITIVE LOGITS
    PMailer
    0.57
    urlpatterns
    0.50
     Ch
    0.49
     chap
    0.47
     mult
    0.44
     bes
    0.44
     Chap
    0.43
     tob
    0.42
     cou
    0.42
    Biographie
    0.41
    Activations Density 1.807%

    No Known Activations