© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1447
    Prev
    Next
    INDEX
    Explanations

    statistics or numbered lists, particularly years

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     myſelf
    -1.55
     itſelf
    -1.45
     ―――――
    -1.39
     Monfieur
    -1.39
     purpoſe
    -1.38
     Theſe
    -1.35
     pleaſure
    -1.35
     Majefty
    -1.34
     ་་
    -1.33
     Efq
    -1.33
    POSITIVE LOGITS
     to
    0.16
     di
    0.10
     in
    0.10
     so
    0.10
     is
    0.07
    ,
    0.06
     and
    0.06
     are
    0.05
     sind
    0.05
     or
    0.04
    Activations Density 4.139%

    No Known Activations