© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16355
    Prev
    Next
    INDEX
    Explanations

    proper nouns and dates from biographical information

    oai_token-act-pair · gemini-2.0-flash

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Roskov
    -0.76
    verifyException
    -0.60
     pomi
    -0.58
     arşivlendi
    -0.56
     sacco
    -0.54
    __(/*!
    -0.54
     Nant
    -0.52
    سى
    -0.51
     lumineuse
    -0.51
    principalColumn
    -0.51
    POSITIVE LOGITS
    umán
    0.51
    EndTag
    0.51
    CLIP
    0.45
    Cursors
    0.45
    TagHelper
    0.44
     Theſe
    0.44
    nameof
    0.44
    ContentAlignment
    0.43
    ADIAN
    0.43
    undial
    0.42
    Activations Density 0.825%

    No Known Activations