© 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. 4814
    Prev
    Next
    INDEX
    Explanations

    terms and names related to geography, tribal history, and scientific publications

    oai_token-act-pair · gemini-2.0-flash

    Polish language/location

    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
    rrggbb
    -0.59
     Италијани
    -0.54
    <?
    -0.49
    XmlEnum
    -0.49
     Chid
    -0.47
    werve
    -0.47
    hastly
    -0.46
     Quora
    -0.45
    therin
    -0.44
    wifery
    -0.43
    POSITIVE LOGITS
    ům
    0.46
    StoryboardSegue
    0.44
    lohy
    0.44
    łady
    0.43
    tvrt
    0.42
    į
    0.42
    łem
    0.41
    ūnas
    0.41
    pravy
    0.41
    likace
    0.41
    Activations Density 11.652%

    No Known Activations