© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4203
    Prev
    Next
    INDEX
    Explanations

    commas, prepositions, conjunctions, and some short words.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     is
    -1.13
     would
    -1.12
     will
    -1.07
     are
    -1.07
     was
    -0.99
     may
    -0.98
     shall
    -0.93
     adalah
    -0.91
     might
    -0.91
     were
    -0.90
    POSITIVE LOGITS
     Monfieur
    0.73
     whoſe
    0.72
    principalTable
    0.70
     myſelf
    0.69
    ècie
    0.68
    GEBURTS
    0.68
     Efq
    0.68
     nonUne
    0.68
     ſta
    0.68
    NameInMap
    0.65
    Activations Density 7.155%

    No Known Activations