© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9814
    Prev
    Next
    INDEX
    Explanations

    words that are domain specific, depending on the context of the sentence (medical, technical, political, etc.)

    oai_token-act-pair · gemini-2.0-flash

    Technical, varied texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ClickListener
    -0.45
    bel
    -0.44
    Widths
    -0.44
    quar
    -0.43
     Road
    -0.42
    tom
    -0.41
    ante
    -0.40
    el
    -0.40
    manni
    -0.39
    yste
    -0.39
    POSITIVE LOGITS
     becauſe
    0.79
     myſelf
    0.77
     purpoſe
    0.77
     ſtate
    0.77
     Efq
    0.75
     fevere
    0.73
     Majefty
    0.71
    SourceChecksum
    0.70
     themſelves
    0.69
     itſelf
    0.69
    Activations Density 4.026%

    No Known Activations