© 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. 10705
    Prev
    Next
    INDEX
    Explanations

    the word 'matrix' and related words or symbols appearing in mathematical discussions

    oai_token-act-pair · gemini-2.0-flash

    matrix

    np_max-act · gemini-2.0-flash
    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
    Portale
    -0.83
     محفوظة
    -0.80
    principalColumn
    -0.79
     незавершена
    -0.79
    Према
    -0.77
    LEncoder
    -0.75
    extAlignment
    -0.75
    PreferredItem
    -0.74
    uxxxx
    -0.71
     consultato
    -0.71
    POSITIVE LOGITS
    kosti
    0.59
    else
    0.56
    e
    0.55
     iconTwitter
    0.53
     aimer
    0.51
    y
    0.50
    aimer
    0.49
    ی
    0.49
    Mr
    0.49
    nullptr
    0.48
    Activations Density 0.674%

    No Known Activations