© 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. 11246
    Prev
    Next
    INDEX
    Explanations

    mentions of foods or meals, often alongside prepositions such as "with" or "of"

    oai_token-act-pair · gemini-2.0-flash

    food reviews

    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
     Monfieur
    -0.65
     Theſe
    -0.64
     tfsi
    -0.64
    AnchorStyles
    -0.63
     Efq
    -0.62
     iſt
    -0.62
     ovp
    -0.61
     Beſ
    -0.60
     étoit
    -0.59
     whoſe
    -0.58
    POSITIVE LOGITS
    wikimedia
    0.54
    ScopeManager
    0.52
     Pra
    0.52
    Datuak
    0.51
     שוליים
    0.49
    jbl
    0.48
    Rptr
    0.47
    hede
    0.47
    Vidite
    0.47
    Jereo
    0.47
    Activations Density 1.081%

    No Known Activations