© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12617
    Prev
    Next
    INDEX
    Explanations

    words related to legal contracts and agreements, with some words pertaining to emotions.

    oai_token-act-pair · gemini-2.0-flash

    Words ending in "er"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ils
    -0.58
    prepareStatement
    -0.55
    ims
    -0.54
    lans
    -0.52
    hogy
    -0.51
    ids
    -0.51
    tices
    -0.50
    mpc
    -0.50
     "..\..\
    -0.50
    __':
    -0.50
    POSITIVE LOGITS
    er
    1.90
    ER
    1.14
    or
    0.82
    erii
    0.82
    eer
    0.80
    ee
    0.80
    erick
    0.77
    ant
    0.76
    erman
    0.76
    erl
    0.75
    Activations Density 5.440%

    No Known Activations