© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15204
    Prev
    Next
    INDEX
    Explanations

    names of middle eastern and turkish dishes

    oai_token-act-pair · gemini-2.0-flash

    dip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    abetes
    -0.65
     svin
    -0.63
    <bos>
    -0.52
    //
    -0.50
     Pig
    -0.50
    Pork
    -0.49
     fondi
    -0.49
     locaux
    -0.49
     Pigs
    -0.49
     curled
    -0.48
    POSITIVE LOGITS
     Exacts
    0.60
    Geplaatst
    0.59
    ГЛА
    0.56
    Gön
    0.55
    omyia
    0.55
     bezeichneter
    0.54
    jstor
    0.53
     Vikipedi
    0.52
    ormal
    0.52
    PreferredItem
    0.51
    Activations Density 5.044%

    No Known Activations