© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1079
    Prev
    Next
    INDEX
    Explanations

    names of people especially those in the Indian film industry, with a focus on connections to the words "will", "be", and "seen".

    oai_token-act-pair · gemini-2.0-flash

    Text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ModelExpression
    -0.46
     @"/
    -0.46
    ftagPool
    -0.46
    ValueGeneration
    -0.43
    TagHelper
    -0.43
    ┛
    -0.41
    Cuánto
    -0.41
    htbp
    -0.41
    ADELPHIA
    -0.40
    consin
    -0.40
    POSITIVE LOGITS
    onViewCreated
    0.69
    BagLayout
    0.61
     feroit
    0.61
    InputBorder
    0.58
    ึ้น
    0.57
     PKK
    0.56
    ImGui
    0.56
     onPostExecute
    0.55
    ArgsConstructor
    0.54
    InBytes
    0.54
    Activations Density 6.370%

    No Known Activations