© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11676
    Prev
    Next
    INDEX
    Explanations

    text related to business-to-business marketing, particularly regarding GPS devices and purchasing decisions

    oai_token-act-pair · gemini-2.0-flash

    End of sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     yet
    -0.47
     AssemblyCompany
    -0.47
    Personendaten
    -0.43
    otá
    -0.42
    wpi
    -0.41
     match
    -0.41
     viewType
    -0.40
    findpost
    -0.40
    .(*
    -0.40
    poved
    -0.40
    POSITIVE LOGITS
     виправивши
    0.66
     intStringLen
    0.65
     <<<<<<<<<<<<<<
    0.59
    ValueGenerated
    0.59
    cshtml
    0.59
     ordinaires
    0.58
    SourceChecksum
    0.57
    SOUNDBITE
    0.56
    insegna
    0.56
     CreateTagHelper
    0.56
    Activations Density 13.703%

    No Known Activations