© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12837
    Prev
    Next
    INDEX
    Explanations

    the word "auto-" or "Auto-"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "auto"

    np_token-act-pair-logits · gpt-4o-mini

    auto

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     médicaux
    -0.54
     professionali
    -0.50
    Hentet
    -0.50
     locaux
    -0.49
     apparti
    -0.48
     amélior
    -0.48
     noires
    -0.48
     kasarigan
    -0.48
     professionisti
    -0.48
     umana
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.89
    DockStyle
    0.63
    labus
    0.60
    Geplaatst
    0.59
    клопе
    0.59
     BrowserModule
    0.57
     regener
    0.57
     يتيمه
    0.56
    HasBeenSet
    0.54
     خارجية
    0.53
    Activations Density 0.524%

    No Known Activations