Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13906
    Prev
    Next
    INDEX
    Explanations

    words referring to validation such as checking, ensuring, verifying, and guaranteeing

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Monfieur
    -0.80
    Personendaten
    -0.75
     Normdatei
    -0.75
     ainfi
    -0.73
    Aiheesta
    -0.72
     Confira
    -0.71
    Confira
    -0.69
     ſtate
    -0.69
     perpetuity
    -0.68
    })*/
    -0.68
    POSITIVE LOGITS
     the
    0.49
     "
    0.45
     Res
    0.45
     i
    0.45
    GroupLayout
    0.44
     an
    0.44
     it
    0.44
     Vil
    0.44
     Sar
    0.43
     Par
    0.43
    Activations Density 36.414%

    No Known Activations