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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11938
    Prev
    Next
    INDEX
    Explanations

    the word "facts" and words that commonly appear in legal documents like "Co" and "respondent"

    oai_token-act-pair · gemini-2.0-flash

    facts

    np_max-act · gemini-2.0-flash

    facts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Co
    -0.76
    *
    -0.75
    0
    -0.75
    ~
    -0.72
    公
    -0.71
    fa
    -0.70
    B
    -0.69
    5
    -0.68
    A
    -0.67
    en
    -0.66
    POSITIVE LOGITS
    ^(@)
    1.19
    LEncoder
    1.03
     AssemblyProduct
    1.01
    ItemBackground
    1.00
    μως
    1.00
     ISNI
    0.98
    EDEFAULT
    0.98
    })*/
    0.96
    ELTS
    0.94
    yntaxException
    0.94
    Activations Density 4.029%

    No Known Activations