© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    parts of words that include the letters "ti", "li", or "ri"

    oai_token-act-pair · gemini-2.0-flash

    ati

    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
     Efq
    -0.77
     الرياضيه
    -0.74
     Majefty
    -0.69
     quelcon
    -0.68
     Jefus
    -0.66
    ьаж
    -0.65
     ſta
    -0.65
     purpoſe
    -0.65
     retrouvé
    -0.63
     myſelf
    -0.63
    POSITIVE LOGITS
     Mérimée
    0.52
     consultato
    0.52
    SequentialGroup
    0.51
     상세
    0.51
     av
    0.48
    /$',
    0.47
     Av
    0.45
    ))[
    0.44
     den
    0.43
    '])->
    0.43
    Activations Density 0.983%

    No Known Activations