© 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. 5118
    Prev
    Next
    INDEX
    Explanations

    lines of code with '@' symbols in them

    oai_token-act-pair · gemini-2.0-flash

    strings starting with an '@' character

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

    @

    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
    วรร
    -0.50
     Q
    -0.49
    bezpe
    -0.47
    خول
    -0.45
     pulito
    -0.44
     sạch
    -0.44
     baratas
    -0.43
     cucharadas
    -0.43
    ménage
    -0.43
    bosity
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.73
    Jereo
    0.60
     beginnetje
    0.60
     whoſe
    0.59
     gynhyrchwyd
    0.59
    AnimationsModule
    0.58
     myſelf
    0.57
     Reſ
    0.57
     itſelf
    0.57
    IndentedString
    0.56
    Activations Density 0.608%

    No Known Activations