© 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. 2906
    Prev
    Next
    INDEX
    Explanations

    words related to asking questions and problem-solving.

    oai_token-act-pair · gemini-2.0-flash

    technical questions and answers

    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
    MockMvc
    -0.75
     Wikispecies
    -0.75
     ExecuteAsync
    -0.71
     فريبيس
    -0.70
     Cedex
    -0.67
     *)__
    -0.66
    autaire
    -0.65
     ujednoznacz
    -0.63
    Personensuche
    -0.63
    medriver
    -0.62
    POSITIVE LOGITS
    ApiModelProperty
    0.59
     aspetto
    0.44
    glDelete
    0.42
    createStatement
    0.42
     faits
    0.41
     blessés
    0.41
     dubbio
    0.41
    MessageOf
    0.40
     pomen
    0.40
     pints
    0.39
    Activations Density 3.062%

    No Known Activations