© 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. 11453
    Prev
    Next
    INDEX
    Explanations

    mentions of team activities and rules

    oai_token-act-pair · gemini-2.0-flash

    Sports training, injuries, codes

    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
     fieldNum
    -0.68
    PreferredItem
    -0.68
    NameInMap
    -0.66
    SharedCtor
    -0.64
    preuve
    -0.57
     Roskov
    -0.56
    ByVersion
    -0.56
    SharedDtor
    -0.56
    RepeatedField
    -0.56
     apellidos
    -0.56
    POSITIVE LOGITS
    hdashline
    0.44
    bigcirc
    0.44
    mada
    0.44
     Zayed
    0.43
    practices
    0.43
     practices
    0.42
    databind
    0.42
    onedDateTime
    0.41
    anstalt
    0.40
    BOU
    0.40
    Activations Density 6.580%

    No Known Activations