© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16075
    Prev
    Next
    INDEX
    Explanations

    a mix of common words, words related to the past, and specific names, without a clear unifying theme.

    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_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
     оригіналу
    -0.59
    webElementXpaths
    -0.54
    ruptedException
    -0.51
    NameInMap
    -0.51
     Newswire
    -0.49
     esternos
    -0.48
    continence
    -0.47
    NegativeButton
    -0.47
    artifactId
    -0.45
    CloseOperation
    -0.45
    POSITIVE LOGITS
    Obrázky
    0.69
    posób
    0.55
    aarrggbb
    0.54
    ngrx
    0.54
    میم
    0.54
    θυ
    0.53
     AssemblyCulture
    0.53
    loroethene
    0.52
     تانيه
    0.51
     Hiram
    0.51
    Activations Density 5.254%

    No Known Activations