© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5809
    Prev
    Next
    INDEX
    Explanations

    capital letters combined with two or three other letters

    oai_token-act-pair · gemini-2.0-flash

    Archaic language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ್
    -0.54
    ්
    -0.51
    dem
    -0.48
    pa
    -0.47
    ks
    -0.44
    dik
    -0.42
    ­
    -0.40
    ́
    -0.39
    chy
    -0.38
    ta
    -0.38
    POSITIVE LOGITS
     Diſ
    0.83
     Efq
    0.77
    ſelf
    0.77
     Monfieur
    0.75
     Conſ
    0.74
     كومونز
    0.73
     Chriftian
    0.73
     Anſ
    0.73
     ſta
    0.72
     ſtate
    0.71
    Activations Density 3.090%

    No Known Activations