© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1503
    Prev
    Next
    INDEX
    Explanations

    certain articles, prepositions and conjunctions, as well as proper nouns, especially when relating to people

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    Xna
    -0.63
     crc
    -0.56
    xC
    -0.56
     Cio
    -0.51
    HIP
    -0.51
    edback
    -0.51
     Niem
    -0.51
    outed
    -0.50
     فريبيس
    -0.50
     newBuilder
    -0.49
    POSITIVE LOGITS
     démocr
    0.65
     enfans
    0.57
    spesies
    0.54
     normaux
    0.54
     kasarigan
    0.52
     ModelExpression
    0.51
     marchés
    0.50
     auraient
    0.50
    })*/
    0.49
     sociaux
    0.47
    Activations Density 0.223%

    No Known Activations