© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5725
    Prev
    Next
    INDEX
    Explanations

    content related to reading reviews

    oai_token-act-pair · gemini-2.0-flash

    requests to read reviews

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

    Read

    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
     CreateTagHelper
    -0.81
    RetentionPolicy
    -0.72
     通販
    -0.70
    ècie
    -0.69
    inaison
    -0.68
    AndEndTag
    -0.68
     myſelf
    -0.68
     Normdatei
    -0.65
     Anſ
    -0.64
     незавершена
    -0.64
    POSITIVE LOGITS
     more
    0.81
     More
    0.71
    more
    0.69
    More
    0.59
     MORE
    0.51
     Lebih
    0.51
     lebih
    0.51
     mehr
    0.50
    UNTAIN
    0.50
     hơn
    0.49
    Activations Density 0.955%

    No Known Activations