© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    the capitalized letters "OS" or words related to fantastical stories, chaos or darkness

    oai_token-act-pair · gemini-2.0-flash

    Chaos

    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
    GEBURTSDATUM
    -0.83
     nahilalakip
    -0.81
     дописавши
    -0.74
    MessageOf
    -0.73
    SPATH
    -0.72
    +#+
    -0.71
    Autoritní
    -0.69
    Hozzáférés
    -0.69
     dAtA
    -0.69
    setVerticalGroup
    -0.68
    POSITIVE LOGITS
     Audiodateien
    0.51
    σμο
    0.45
     bebas
    0.44
    衆
    0.44
    bose
    0.42
     free
    0.42
     tormenta
    0.42
    Handel
    0.41
     void
    0.41
    Syria
    0.40
    Activations Density 1.413%

    No Known Activations