© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4283
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and commas in the beginning, middle, or end of a sentence

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    bkz
    -0.48
    Thành
    -0.48
    unhofer
    -0.45
     لیگ
    -0.44
    stø
    -0.42
     olympiques
    -0.41
    Và
    -0.39
    pygame
    -0.39
     grå
    -0.39
     screwdriver
    -0.39
    POSITIVE LOGITS
    ագրություններ
    0.77
    GOTREF
    0.75
    Бахар
    0.73
    BeginContext
    0.72
    CloseOperation
    0.71
    ]),
    0.70
    ]]);
    0.70
    Personendaten
    0.69
    AppMethodBeat
    0.68
     للمعارف
    0.67
    Activations Density 2.452%

    No Known Activations