© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5813
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to descriptions of documents or speech.

    oai_token-act-pair · gemini-2.0-flash

    say "th" words

    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
     AssemblyCulture
    -0.68
     MainAxisSize
    -0.66
    MLLoader
    -0.63
    GOTREF
    -0.63
     Normdatei
    -0.59
     CreateTagHelper
    -0.59
    consulté
    -0.57
     ElementRef
    -0.57
    Carriera
    -0.57
     unknownFields
    -0.57
    POSITIVE LOGITS
     th
    2.05
     thi
    1.52
     Th
    1.44
    Th
    1.41
     tha
    1.41
     TH
    1.30
     t
    1.24
    th
    1.22
     ther
    1.15
     thr
    1.13
    Activations Density 6.164%

    No Known Activations