© 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. 10601
    Prev
    Next
    INDEX
    Explanations

    second person pronouns and commands

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'log'

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

    Log in

    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
     AssemblyVersion
    -0.83
     ostavi
    -0.61
    orianCalendar
    -0.57
     DMD
    -0.55
    Décès
    -0.55
    \}_{
    -0.53
     Roskov
    -0.52
    delmi
    -0.52
    ัฒนา
    -0.51
     tartalomajánló
    -0.51
    POSITIVE LOGITS
     log
    1.70
     logged
    1.50
     Log
    1.49
    Log
    1.48
    log
    1.46
     logging
    1.46
     logs
    1.30
     LOG
    1.28
     Logging
    1.23
    LOG
    1.19
    Activations Density 3.522%

    No Known Activations