© 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. 11863
    Prev
    Next
    INDEX
    Explanations

    common words such as pronouns, prepositions and articles

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "name"

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

    name

    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
    ifrance
    -0.46
    Signin
    -0.43
    OrBuilder
    -0.42
    łaści
    -0.40
     verke
    -0.36
    kij
    -0.36
     φο
    -0.36
     könnt
    -0.36
    áda
    -0.36
    らせる
    -0.35
    POSITIVE LOGITS
     name
    3.38
    Name
    2.98
     Name
    2.80
    name
    2.75
     names
    2.52
     NAME
    2.52
    NAME
    2.30
     Namen
    2.14
     naam
    2.05
     Names
    2.02
    Activations Density 1.125%

    No Known Activations