© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    strings in a programming language

    oai_token-act-pair · 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
     régulier
    -0.60
     vôtre
    -0.52
    Arg
    -0.52
     bén
    -0.51
    Asn
    -0.51
    Var
    -0.50
    Meta
    -0.49
    Arr
    -0.49
    Sequ
    -0.49
    Lens
    -0.49
    POSITIVE LOGITS
    RTEE
    0.56
     ProtoMessage
    0.52
    AddHtmlAttribute
    0.45
     CreateTagHelper
    0.44
    GEBURTSDATUM
    0.44
    RTEX
    0.39
    photobucket
    0.38
     CURIAM
    0.37
    tagHelperRunner
    0.37
    protoimpl
    0.36
    Activations Density 4.848%

    No Known Activations