© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4303
    Prev
    Next
    INDEX
    Explanations

    HTML tags containing URLs, especially those starting with "https", as well as some date-like strings and some words relating to blog posts

    oai_token-act-pair · gemini-2.0-flash

    URLs and code

    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
     I
    -1.77
     A
    -1.52
     It
    -1.42
     In
    -1.36
     "
    -1.36
     We
    -1.35
     i
    -1.33
     As
    -1.33
     The
    -1.31
     And
    -1.31
    POSITIVE LOGITS
     itſelf
    1.77
     myſelf
    1.59
     Monfieur
    1.57
     Majefty
    1.55
     raiſ
    1.52
     pleaſure
    1.50
     Houſe
    1.49
     Diſ
    1.45
     purpoſe
    1.42
     Anſ
    1.41
    Activations Density 14.208%

    No Known Activations