© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6876
    Prev
    Next
    INDEX
    Explanations

    words and phrases in multiple languages related to software and computers

    oai_token-act-pair · gemini-2.0-flash

    text starting with specific prefixes or characters

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

    non-English languages

    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
     Efq
    -1.10
     nahilalakip
    -1.02
    UserScript
    -0.98
     estekak
    -0.98
     Мексичка
    -0.96
     Eſ
    -0.96
     للمعارف
    -0.96
     Diſ
    -0.95
     فريبيس
    -0.94
     Cæsar
    -0.94
    POSITIVE LOGITS
     comp
    0.60
     pro
    0.47
     de
    0.44
     di
    0.42
     про
    0.41
     F
    0.41
     ve
    0.41
     rep
    0.40
     I
    0.40
     «
    0.40
    Activations Density 0.872%

    No Known Activations