© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2070
    Prev
    Next
    INDEX
    Explanations

    short, common words like prepositions, articles, conjunctions, and other grammatical connectors.

    oai_token-act-pair · gemini-2.0-flash

    say the ending -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     purpoſe
    -1.38
     ſtate
    -1.36
     myſelf
    -1.35
     fhew
    -1.30
     themſelves
    -1.29
     uſe
    -1.28
     ſeveral
    -1.26
     Efq
    -1.26
     ftate
    -1.25
     ſtand
    -1.24
    POSITIVE LOGITS
     reading
    0.63
     serving
    0.57
     fighting
    0.57
     checking
    0.54
     exploring
    0.54
     en
    0.53
     pushing
    0.52
     accessing
    0.52
     taking
    0.52
     talking
    0.51
    Activations Density 2.344%

    No Known Activations